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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 3-RES-JB
    6. 21509
    Prev
    Next
    INDEX
    Explanations

    references to the "Justice Department."

    oai_token-act-pair · gpt-3.5-turbo

    references to governmental departments, specifically the Justice Department

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vari
    -0.83
    rave
    -0.82
     sidx
    -0.76
     externalToEVAOnly
    -0.73
    à¸
    -0.71
    piring
    -0.70
    yip
    -0.70
    rang
    -0.69
    onen
    -0.69
    oute
    -0.68
    POSITIVE LOGITS
     Department
    0.96
     Agency
    0.88
     Dept
    0.86
     executive
    0.85
     Office
    0.83
     Executive
    0.82
     treasury
    0.82
     Accountability
    0.81
     coffers
    0.81
     secretary
    0.80
    Activations Density 0.034%

    No Known Activations