© 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 EvalsExportsinterp-engineNEWAPI 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. 14053
    Prev
    Next
    INDEX
    Explanations

    references to legal or political entities, particularly focused on legal cases and official titles

    oai_token-act-pair · gpt-3.5-turbo

    the presence of specific abbreviations or acronyms in a political context, particularly related to judicial references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     levers
    -0.71
    staking
    -0.59
    unal
    -0.59
    ahime
    -0.55
     yes
    -0.54
     applicable
    -0.54
     ha
    -0.54
     manif
    -0.54
     commercially
    -0.54
    dict
    -0.54
    POSITIVE LOGITS
    Va
    1.14
    Gray
    0.95
    C
    0.91
    Calif
    0.83
    HI
    0.81
    INO
    0.80
    IA
    0.75
     Rockefeller
    0.74
    RAW
    0.74
    J
    0.72
    Activations Density 0.020%

    No Known Activations