© 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. 9-RES-JB
    11. 19380
    Prev
    Next
    INDEX
    Explanations

    proper nouns like names of companies, organizations, and individuals

    oai_token-act-pair · gpt-3.5-turbo

    names of organizations and institutions

    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
    abiding
    -0.76
     "$:/
    -0.73
     trillions
    -0.72
    ecast
    -0.70
    rha
    -0.69
    obyl
    -0.69
    rations
    -0.69
    NetMessage
    -0.68
    piring
    -0.68
     barg
    -0.68
    POSITIVE LOGITS
     spokesman
    1.76
     spokesperson
    1.76
     spokeswoman
    1.74
     spokes
    1.23
     representative
    1.14
     deputy
    1.08
     director
    1.08
     official
    1.08
     attorney
    1.07
     Director
    1.05
    Activations Density 0.439%

    No Known Activations