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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 6889
    Prev
    Next
    INDEX
    Explanations

    proper nouns and names of people or places

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns or names of individuals

    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
     maid
    -0.77
     womb
    -0.73
    wcs
    -0.72
     miscarriage
    -0.71
     pregnancy
    -0.71
     Parenthood
    -0.70
    actionDate
    -0.69
     CODE
    -0.69
     ANGEL
    -0.68
     maiden
    -0.66
    POSITIVE LOGITS
     himself
    1.15
     Sr
    0.95
     Jr
    0.91
     Himself
    0.78
    gaard
    0.77
     admits
    0.75
     enjoys
    0.73
     personally
    0.72
    ouf
    0.72
    isky
    0.70
    Activations Density 0.519%

    No Known Activations