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. 1-RES-JB
    6. 18225
    Prev
    Next
    INDEX
    Explanations

    references to titles or sections of legal documents, particularly focusing on Title IX

    oai_token-act-pair · gpt-3.5-turbo

    references to specific titles of laws or regulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     detachment
    -0.77
     elector
    -0.70
    ITH
    -0.68
     electors
    -0.67
     sten
    -0.66
     circulation
    -0.66
     thermal
    -0.65
     spontaneous
    -0.64
    dyl
    -0.64
     engagement
    -0.63
    POSITIVE LOGITS
     Title
    1.13
    Title
    1.05
    title
    1.02
    itles
    0.99
    \\\\\\\\
    0.89
    eous
    0.88
    cknowled
    0.82
    istries
    0.79
    yright
    0.78
     IX
    0.78
    Activations Density 0.006%

    No Known Activations