© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 10347
    Prev
    Next
    INDEX
    Explanations

    law firms and companies, possibly related to legal matters from various legal, business, and social contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to specific organizations or brand names

    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
     Sorce
    -0.63
    pter
    -0.62
     showc
    -0.61
     Lauder
    -0.60
    advertisement
    -0.59
    repeat
    -0.58
    vp
    -0.57
    oxide
    -0.57
    facing
    -0.56
     polar
    -0.55
    POSITIVE LOGITS
    wana
    0.96
    levard
    0.92
    apest
    0.85
    lehem
    0.85
    EStreamFrame
    0.85
    aneers
    0.84
    ÃĽ
    0.81
    LEY
    0.78
    leck
    0.77
    reau
    0.76
    Activations Density 0.446%

    No Known Activations