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. 9-RES-JB
    6. 598
    Prev
    Next
    INDEX
    Explanations

    titles or subtitles related to the conclusion or final part of a series or story

    oai_token-act-pair · gpt-3.5-turbo

    closing parentheses in text, likely indicating titles or sections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     answ
    -0.76
    bably
    -0.75
     artif
    -0.70
    ãĥ¥
    -0.69
     footing
    -0.67
    itory
    -0.65
    matically
    -0.65
    stead
    -0.64
    tering
    -0.64
    bed
    -0.63
    POSITIVE LOGITS
     âĵĺ
    0.95
    ↵↵
    0.83
    ↵
    0.83
     |
    0.82
     =>
    0.79
     Committees
    0.78
     :
    0.77
     –
    0.77
     âĨĴ
    0.77
     ;
    0.76
    Activations Density 0.121%

    No Known Activations