Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 3770
    Prev
    Next
    INDEX
    Explanations

    descriptions related to legal proceedings like bails and bonds

    oai_token-act-pair · gpt-3.5-turbo

    terms related to bail and legal bonds

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ¡
    -0.68
     Generations
    -0.66
    onnaissance
    -0.66
    zinski
    -0.66
    OY
    -0.64
    ORPG
    -0.63
    advertisement
    -0.63
    urger
    -0.63
    culosis
    -0.62
     Pixel
    -0.62
    POSITIVE LOGITS
     arra
    1.05
     pending
    0.93
     plea
    0.92
     Detention
    0.92
     hearings
    0.86
     affidavit
    0.85
     adjourn
    0.85
     detention
    0.83
    ansas
    0.82
    istrates
    0.81
    Activations Density 0.083%

    No Known Activations