© 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. 9-RES-JB
    11. 2379
    Prev
    Next
    INDEX
    Explanations

    references to specific locations or sources

    oai_token-act-pair · gpt-3.5-turbo

    references to figures or visual representations

    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
    biased
    -0.78
    bably
    -0.77
    âĹ¼
    -0.76
    onz
    -0.75
    cffffcc
    -0.74
    operated
    -0.73
    icum
    -0.71
    ersive
    -0.70
    opped
    -0.70
    affle
    -0.69
    POSITIVE LOGITS
     below
    1.19
     sidebar
    0.97
     above
    0.95
     supra
    0.91
     Appendix
    0.88
     footnote
    0.87
     www
    0.82
     FAQ
    0.81
     Below
    0.79
     http
    0.78
    Activations Density 0.033%

    No Known Activations