© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 24226
    Prev
    Next
    INDEX
    Explanations

    sentences that end with a period, especially those that conclude a short, impactful statement or surprising fact.

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered by @danielepoterti

    sentences related to unusual or dramatic events with variable characters and actions involved

    oai_token-act-pair · gpt-3.5-turbo

    sentences that convey a sense of absurdity or surreal humor

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     consolidation
    -1.02
     consolidated
    -0.90
     affili
    -0.87
     organis
    -0.86
     consolid
    -0.84
     satell
    -0.83
     acquisitions
    -0.82
     migration
    -0.79
     broadly
    -0.79
     holdings
    -0.78
    POSITIVE LOGITS
     Turns
    1.28
     Needless
    1.27
     Oops
    1.27
     Funny
    1.26
     Sounds
    1.23
     Apparently
    1.20
     Luckily
    1.18
     Naturally
    1.18
     Thankfully
    1.15
     Seriously
    1.15
    Activations Density 0.572%

    No Known Activations