© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 460
    Prev
    Next
    INDEX
    Explanations

    instances where a public prosecutor or prosecution-related terms are mentioned

    oai_token-act-pair · gpt-3.5-turbo

    references to legal professionals, specifically prosecutors

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

    No Comments

    Negative Logits
    yip
    -0.74
    forward
    -0.68
    erd
    -0.68
    eating
    -0.68
    airs
    -0.65
     taste
    -0.64
    lihood
    -0.64
    roots
    -0.64
    birth
    -0.63
    Hop
    -0.63
    POSITIVE LOGITS
     prosecutor
    0.85
     Prosecutor
    0.79
     subpoen
    0.75
     prosecuted
    0.75
     indicted
    0.74
     thous
    0.74
    itatively
    0.74
     investigator
    0.72
    deen
    0.71
     investigating
    0.70
    Activations Density 0.016%

    No Known Activations