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. 18024
    Prev
    Next
    INDEX
    Explanations

    references to legal actions or legal professionals, particularly prosecutors

    oai_token-act-pair · gpt-3.5-turbo

    mentions of prosecutors in relation to legal proceedings

    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
    yip
    -0.76
    oken
    -0.72
    lihood
    -0.70
    forward
    -0.69
    omach
    -0.67
    birth
    -0.67
    Wo
    -0.66
    wo
    -0.65
    opian
    -0.65
    patch
    -0.64
    POSITIVE LOGITS
     prosecutor
    0.91
     indicted
    0.89
     investigator
    0.87
     prosecutors
    0.86
    heet
    0.82
     investigating
    0.82
     prosecuted
    0.82
     proced
    0.82
     allege
    0.78
     subpoen
    0.78
    Activations Density 0.013%

    No Known Activations