© 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. 10-RES-JB
    11. 18984
    Prev
    Next
    INDEX
    Explanations

    technical terms related to computer programming and technology

    oai_token-act-pair · gpt-3.5-turbo

    references to financial instruments and applications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gently
    -0.60
    Rated
    -0.59
    $.
    -0.58
    anwhile
    -0.58
    poral
    -0.57
    ragon
    -0.56
    ighter
    -0.56
     Ambro
    -0.55
    .''.
    -0.55
    ãĤ¦ãĤ¹
    -0.55
    POSITIVE LOGITS
    ,
    0.79
    *,
    0.71
     foregoing
    0.69
     fiasco
    0.68
     aforementioned
    0.67
    !,
    0.67
    (),
    0.65
     debacle
    0.64
     caveats
    0.63
    ,[
    0.62
    Activations Density 0.411%

    No Known Activations