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. 8-RES-JB
    6. 21975
    Prev
    Next
    INDEX
    Explanations

    mentions of legal and political actions or decisions

    oai_token-act-pair · gpt-3.5-turbo

    instances of numerical values or ratings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ĥ
    -0.90
    ©
    -0.85
    poon
    -0.78
    ¡
    -0.73
    ¥µ
    -0.72
    ¬
    -0.70
    baugh
    -0.69
    Ĥ¬
    -0.68
    Ĭ
    -0.67
    ī
    -0.67
    POSITIVE LOGITS
    FILE
    1.22
    Fresh
    0.76
    Returns
    0.71
    ³³³³³³³³
    0.70
    Actor
    0.69
    Shell
    0.69
    IJ
    0.69
    âĵĺ
    0.68
    Credit
    0.67
    article
    0.67
    Activations Density 0.076%

    No Known Activations