© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 10271
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and symbols

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, specifically parentheses and closing marks

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

    No Comments

    Negative Logits
    iates
    -0.72
    ilee
    -0.67
    ework
    -0.66
     eyeb
    -0.65
     deleg
    -0.64
    itiz
    -0.63
    yright
    -0.63
     cohesion
    -0.61
     yourselves
    -0.61
     mort
    -0.61
    POSITIVE LOGITS
    âķ
    0.85
    20439
    0.78
    ï¸
    0.78
    âķIJ
    0.77
    Fri
    0.75
    RESULTS
    0.73
    è¦ļéĨĴ
    0.71
    RANT
    0.68
     Runs
    0.66
    TN
    0.66
    Activations Density 0.091%

    No Known Activations