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. 21314
    Prev
    Next
    INDEX
    Explanations

    specific punctuation marks

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, specifically semicolons

    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
    ©¶æ¥µ
    -0.87
    omorphic
    -0.76
    ema
    -0.73
    rio
    -0.71
    din
    -0.70
    se
    -0.69
    ero
    -0.68
    odes
    -0.68
    ħĭ
    -0.67
    senal
    -0.66
    POSITIVE LOGITS
     furthermore
    0.94
     thence
    0.94
     alternatively
    0.91
    âĢ¢âĢ¢âĢ¢âĢ¢
    0.88
    -)
    0.88
     moreover
    0.85
     Flavoring
    0.85
     meanwhile
    0.81
    âĢ¢âĢ¢
    0.80
     };
    0.79
    Activations Density 0.043%

    No Known Activations