© 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. 11-RES-JB
    11. 12634
    Prev
    Next
    INDEX
    Explanations

    dates mentioned in the text

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, specifically periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tremend
    -0.84
     calming
    -0.81
     ingrained
    -0.80
     resil
    -0.80
     metic
    -0.78
     ingred
    -0.77
     flourishing
    -0.76
     disadvant
    -0.76
     downright
    -0.76
     overpower
    -0.74
    POSITIVE LOGITS
    <|endoftext|>
    1.66
     ®
    1.35
     Stay
    1.34
     Tickets
    1.32
     Anyone
    1.28
     Visit
    1.23
     Pricing
    1.23
     Expect
    1.22
     Proceed
    1.22
     Details
    1.21
    Activations Density 0.291%

    No Known Activations