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. 6-RES-JB
    6. 21528
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal bail processes

    oai_token-act-pair · gpt-3.5-turbo

    references to bail in legal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     TABLE
    -0.75
    æŃ¦
    -0.74
    advertisement
    -0.73
    ROR
    -0.72
    heny
    -0.71
    urrent
    -0.70
    xual
    -0.70
    urger
    -0.69
    orrect
    -0.69
     Generations
    -0.66
    POSITIVE LOGITS
    iffs
    1.05
     bail
    0.95
    iff
    0.85
    outs
    0.83
    IER
    0.82
     bonds
    0.77
     Bonds
    0.73
     bailed
    0.72
     bond
    0.70
    iw
    0.68
    Activations Density 0.013%

    No Known Activations