Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 10294
    Prev
    Next
    INDEX
    Explanations

    keywords related to committees and organizational procedures

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "committee."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    laus
    -0.74
    Pear
    -0.67
     Fasc
    -0.66
     fasc
    -0.65
     Primal
    -0.64
    mx
    -0.64
    ties
    -0.63
     Tide
    -0.62
    VIDEO
    -0.62
    comes
    -0.61
    POSITIVE LOGITS
     committees
    1.09
     committee
    1.06
    ittee
    0.97
    ittees
    0.96
     chairman
    0.94
     chair
    0.90
     hearings
    0.89
    rons
    0.89
     chairs
    0.86
    chairs
    0.85
    Activations Density 0.014%

    No Known Activations