© 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. 8-RES-JB
    11. 7580
    Prev
    Next
    INDEX
    Explanations

    instances of periods followed by quotations or specific sequences of characters, potentially related to coding or formatting

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks and sentence endings

    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
     Aires
    -0.70
     favour
    -0.68
    xual
    -0.67
    agar
    -0.62
     POV
    -0.61
     Venom
    -0.61
     Princ
    -0.61
     rumours
    -0.60
     estates
    -0.60
     cit
    -0.60
    POSITIVE LOGITS
    SHARE
    1.11
    Except
    1.00
    But
    0.99
    And
    0.95
    Yet
    0.95
    Especially
    0.91
    Then
    0.89
    Priv
    0.89
    That
    0.89
    Repeat
    0.89
    Activations Density 0.439%

    No Known Activations