© 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. 4-RES-JB
    11. 14800
    Prev
    Next
    INDEX
    Explanations

    references to different segments or sections within a larger entity or organization

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "division" and its usage in various contexts

    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
    jamin
    -0.66
    formed
    -0.65
    uated
    -0.64
    icial
    -0.63
    ãĤ§
    -0.63
    CHA
    -0.62
    figure
    -0.61
    lex
    -0.61
    aimon
    -0.61
    plays
    -0.61
    POSITIVE LOGITS
    naire
    0.98
     division
    0.96
     divisions
    0.94
     fronts
    0.86
    al
    0.83
    ally
    0.80
    alities
    0.76
    ISION
    0.74
     fractions
    0.72
    edly
    0.72
    Activations Density 0.011%

    No Known Activations