© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7-RES-JB
    11. 1865
    Prev
    Next
    INDEX
    Explanations

    descriptions of criminal activities or legal proceedings

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to legal matters and convictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CONCLUS
    -0.86
    )).
    -0.86
    Conclusion
    -0.85
    .).
    -0.75
    ))))
    -0.73
    )))
    -0.73
    natureconservancy
    -0.72
     etc
    -0.70
    endif
    -0.70
    ]).
    -0.69
    POSITIVE LOGITS
     Thursday
    0.75
     Wednesday
    0.73
     Tuesday
    0.70
     Monday
    0.67
     Friday
    0.64
    neau
    0.59
     lodged
    0.58
     Integrated
    0.58
     Updated
    0.57
     flagged
    0.57
    Activations Density 2.034%

    No Known Activations