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

    Neuronpedia

    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. 21698
    Prev
    Next
    INDEX
    Explanations

    mentions of sports teams and players

    oai_token-act-pair · gpt-3.5-turbo

    sentences that indicate ranking or evaluation of performance

    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
     interpre
    -0.81
     terminated
    -0.73
     deceived
    -0.73
     legally
    -0.72
     que
    -0.72
     mislead
    -0.72
     programmed
    -0.71
     unidentified
    -0.70
     charged
    -0.69
     interpreted
    -0.69
    POSITIVE LOGITS
    Conclusion
    1.27
    Notable
    1.15
    Overall
    1.11
    CONCLUS
    1.09
    Advertisements
    1.09
    Anyway
    1.09
    Grade
    1.07
    Favorite
    1.05
    Pros
    1.04
    Pred
    1.04
    Activations Density 0.347%

    No Known Activations