© 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. 11-RES-JB
    11. 7144
    Prev
    Next
    INDEX
    Explanations

    pairs of entities or people that are mentioned together in a document

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    only
    -0.73
    ventory
    -0.73
    reth
    -0.73
    spection
    -0.71
    livion
    -0.70
    =-=-
    -0.70
    etter
    -0.69
    alion
    -0.68
    dad
    -0.68
     Pastebin
    -0.68
    POSITIVE LOGITS
     equally
    0.94
     excellent
    0.89
     vying
    0.88
     sexes
    0.87
     extremes
    0.84
     strengths
    0.83
     trademarks
    0.82
     positives
    0.81
     examples
    0.80
    ocating
    0.78
    Activations Density 0.133%

    No Known Activations