© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 20874
    Prev
    Next
    INDEX
    Explanations

    phrases related to disproportional distributions or impacts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to disproportionate impacts or inequalities affecting specific groups

    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
    shire
    -0.79
    hus
    -0.79
    ince
    -0.77
    love
    -0.75
    uring
    -0.75
    icist
    -0.74
    adal
    -0.74
    ode
    -0.73
    sein
    -0.73
    icism
    -0.73
    POSITIVE LOGITS
     disproportion
    0.98
     disproportionately
    0.91
     disadvant
    0.84
     amounts
    0.78
     disadvantage
    0.77
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    0.75
     impacts
    0.75
    pling
    0.75
     representation
    0.75
     disadvantages
    0.74
    Activations Density 0.022%

    No Known Activations