© 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. 0-RES-JB
    11. 1078
    Prev
    Next
    INDEX
    Explanations

    specific instances where the word "division" is mentioned in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to organizational or military divisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    emort
    -0.85
     Logged
    -0.83
     Ambro
    -0.76
    bek
    -0.75
    hots
    -0.75
    achy
    -0.66
    ãĤ¯
    -0.66
    anke
    -0.64
     Haunted
    -0.64
    asio
    -0.63
    POSITIVE LOGITS
     division
    4.03
     divisions
    2.98
    division
    2.53
     Division
    2.43
    Div
    1.61
     divide
    1.52
     subdivision
    1.49
     Div
    1.41
     dividing
    1.40
     divides
    1.34
    Activations Density 0.019%

    No Known Activations