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. 0-RES-JB
    6. 8939
    Prev
    Next
    INDEX
    Explanations

    organizations or groups related to civil liberties

    oai_token-act-pair · gpt-3.5-turbo

    mentions of civil liberties organizations

    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
     amnesty
    -0.88
     contr
    -0.76
     abort
    -0.70
    baby
    -0.70
     camp
    -0.68
     notebook
    -0.65
     messaging
    -0.63
    oys
    -0.63
     overtime
    -0.63
     pickup
    -0.63
    POSITIVE LOGITS
     Liberties
    4.63
     liberties
    0.96
     ACLU
    0.90
     Libraries
    0.89
    merce
    0.86
     Publishers
    0.86
    tein
    0.86
     Bened
    0.86
     Lawyers
    0.85
     Rights
    0.84
    Activations Density 0.013%

    No Known Activations