© 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. 8-RES-JB
    11. 19419
    Prev
    Next
    INDEX
    Explanations

    phrases related to effort or achievement

    oai_token-act-pair · gpt-3.5-turbo

    words related to personal development and growth

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Tycoon
    -0.72
    adan
    -0.67
    Ĥª
    -0.65
    arettes
    -0.63
    amaz
    -0.63
     Shake
    -0.62
    adra
    -0.60
    externalActionCode
    -0.60
    ĺħ
    -0.59
    angan
    -0.59
    POSITIVE LOGITS
    own
    0.94
    ancer
    0.94
    escription
    0.90
    paren
    0.85
    icular
    0.82
    igion
    0.82
    dit
    0.79
    ouble
    0.78
    iatrics
    0.77
    inal
    0.72
    Activations Density 0.259%

    No Known Activations