© 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 EvalsExportsAPI 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. 4-RES-JB
    11. 17002
    Prev
    Next
    INDEX
    Explanations

    names containing "Kn" and words related to tools or objects depicting action

    oai_token-act-pair · gpt-3.5-turbo

    words beginning with the letters "kn" or related to knowledge and understanding

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

    No Comments

    Negative Logits
    hetical
    -0.78
     showc
    -0.77
    tnc
    -0.77
    catentry
    -0.71
    ICAN
    -0.71
    llah
    -0.68
    asive
    -0.64
    anwhile
    -0.63
     impair
    -0.63
    ascript
    -0.63
    POSITIVE LOGITS
    pton
    0.92
    edge
    0.86
    pps
    0.85
     nails
    0.77
    itzer
    0.76
    Kn
    0.70
    puff
    0.70
    Accept
    0.69
    NK
    0.68
    Anne
    0.68
    Activations Density 0.157%

    No Known Activations