© 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. 18438
    Prev
    Next
    INDEX
    Explanations

    parenthetical statements

    oai_token-act-pair · gpt-3.5-turbo

    opening parentheses in sentences

    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
     inund
    -0.80
     undet
    -0.80
     stagn
    -0.77
     spir
    -0.76
     pudding
    -0.73
     exemplary
    -0.73
    ogly
    -0.73
     footing
    -0.72
     appropri
    -0.72
     estab
    -0.72
    POSITIVE LOGITS
    âĢ¦)
    1.35
    Though
    1.25
    See
    1.23
    Ironically
    1.20
    Laughs
    1.20
    RELATED
    1.20
    Also
    1.19
    Unless
    1.19
    hide
    1.18
    laughs
    1.16
    Activations Density 0.049%

    No Known Activations