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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 17934
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal charges being filed against individuals

    oai_token-act-pair · gpt-3.5-turbo

    mentions of charges or accusations 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 @ 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
    ÃŁ
    -0.88
    ãĥ©ãĥ³
    -0.87
    hops
    -0.85
    ãĤ¡
    -0.84
     teasp
    -0.83
    inventoryQuantity
    -0.81
    swick
    -0.80
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.78
    soDeliveryDate
    -0.78
    ãĥ¼ãĤ¯
    -0.77
    POSITIVE LOGITS
     him
    0.95
     behalf
    0.90
     anyone
    0.83
     anybody
    0.81
    gery
    0.79
     individuals
    0.79
     whom
    0.77
     humanity
    0.76
     whoever
    0.76
     suspects
    0.75
    Activations Density 0.037%

    No Known Activations