© 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. 12-RES-JB
    11. 3171
    Prev
    Next
    INDEX
    Explanations

    promotional offers related to digital access and subscriptions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    references to access and subscription details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
    terness
    -0.94
    gdala
    -0.94
    erity
    -0.91
    itaire
    -0.89
     Vaugh
    -0.89
    artney
    -0.88
    Downloadha
    -0.87
    ertodd
    -0.86
    abwe
    -0.85
    iatus
    -0.85
    POSITIVE LOGITS
     major
    1.21
     current
    1.20
     national
    1.13
     professional
    1.10
     human
    1.08
     regular
    1.07
     popular
    1.06
     public
    1.03
     large
    1.03
     international
    1.01
    Activations Density 0.063%

    No Known Activations