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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 5-RES-JB
    6. 21922
    Prev
    Next
    INDEX
    Explanations

    political and social commentary

    oai_token-act-pair · gpt-3.5-turbo

    references to collective identity and societal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Editorial
    -0.53
     Tropical
    -0.49
     KR
    -0.48
     Release
    -0.48
     Err
    -0.47
     FY
    -0.46
     ACTIONS
    -0.46
     Announce
    -0.46
     CCP
    -0.45
     Releases
    -0.45
    POSITIVE LOGITS
    )."
    1.00
    ").
    0.89
    ]."
    0.86
    .'"
    0.83
    ."[
    0.82
    ".[
    0.80
    ).[
    0.79
    '."
    0.79
    ?".
    0.73
     â̦"
    0.73
    Activations Density 2.346%

    No Known Activations