© 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. 9-RES-JB
    11. 7242
    Prev
    Next
    INDEX
    Explanations

    mentions of legal or official changes or additions

    oai_token-act-pair · gpt-3.5-turbo

    references to legislative amendments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    INESS
    -0.82
    ordon
    -0.79
     Tycoon
    -0.77
    vana
    -0.77
    llah
    -0.71
     quarters
    -0.69
     Pry
    -0.69
    soever
    -0.68
    wan
    -0.68
    doms
    -0.68
    POSITIVE LOGITS
     thereto
    0.98
    xual
    0.81
     amendments
    0.80
    witz
    0.80
     banning
    0.77
     amendment
    0.75
     Amendments
    0.75
     wording
    0.75
     amend
    0.73
     abol
    0.73
    Activations Density 0.061%

    No Known Activations