© 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. 2431
    Prev
    Next
    INDEX
    Explanations

    phrases where someone is speaking

    oai_token-act-pair · gpt-3.5-turbo

    direct quotations or reported speech

    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
    inary
    -0.71
     Organization
    -0.63
     caliber
    -0.62
    lection
    -0.59
    ormal
    -0.58
     Organisation
    -0.58
     missed
    -0.58
     simultaneous
    -0.57
     Unic
    -0.55
     legalized
    -0.55
    POSITIVE LOGITS
    advertisement
    0.81
     challeng
    0.80
    ometimes
    0.77
    hiba
    0.77
     diplom
    0.74
     confidently
    0.73
    ansky
    0.73
    olate
    0.71
    omething
    0.70
    PLIED
    0.69
    Activations Density 0.109%

    No Known Activations