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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 21019
    Prev
    Next
    INDEX
    Explanations

    mentions of bail conditions in legal contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to bail in a legal context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æŃ¦
    -0.79
     TABLE
    -0.79
    itamin
    -0.70
    American
    -0.69
    advertisement
    -0.69
    WHO
    -0.69
    xual
    -0.67
    ebook
    -0.67
    urger
    -0.67
    orrect
    -0.66
    POSITIVE LOGITS
    iffs
    1.04
     bail
    1.03
    iff
    0.86
    IER
    0.79
    outs
    0.79
    ignt
    0.77
     Deposit
    0.75
     uncond
    0.72
    oning
    0.71
     bonds
    0.71
    Activations Density 0.010%

    No Known Activations