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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 7-RES-JB
    6. 10641
    Prev
    Next
    INDEX
    Explanations

    statements or questions related to actions or consequences

    oai_token-act-pair · gpt-3.5-turbo

    phrases that involve people discussing topics related to communities and social interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Hass
    -0.67
    atl
    -0.64
     Icelandic
    -0.60
     Mous
    -0.56
    annis
    -0.56
    tsky
    -0.55
    tyard
    -0.55
     Bru
    -0.55
    Ruby
    -0.54
    uli
    -0.54
    POSITIVE LOGITS
    azo
    0.76
    '>
    0.73
    ',"
    0.65
     automatically
    0.64
    morrow
    0.64
    Leaks
    0.64
     damn
    0.63
    ulla
    0.62
     gonna
    0.61
    etheless
    0.60
    Activations Density 0.667%

    No Known Activations