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. 6231
    Prev
    Next
    INDEX
    Explanations

    mentions of legal terms related to post-conviction monitoring such as "probation" and "parole"

    oai_token-act-pair · gpt-3.5-turbo

    references to probation and related legal terminology

    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
    Dust
    -0.69
    989
    -0.66
    ãĤ¨
    -0.64
    Downloadha
    -0.62
    lycer
    -0.62
    bern
    -0.62
    rencies
    -0.61
    ffee
    -0.61
    ombies
    -0.61
    æŃ¦
    -0.60
    POSITIVE LOGITS
     probation
    1.17
     parole
    0.92
    ary
    0.86
     revocation
    0.85
     confir
    0.84
    ally
    0.81
    urous
    0.79
    atory
    0.75
    ishment
    0.73
     violation
    0.73
    Activations Density 0.013%

    No Known Activations