© 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. 10-RES-JB
    11. 17376
    Prev
    Next
    INDEX
    Explanations

    mentions of entities involved in legal investigations

    oai_token-act-pair · gpt-3.5-turbo

    references to investigative proceedings and inquiries involving Robert Mueller

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Quantity
    -0.83
    æ©
    -0.78
     marg
    -0.72
     vending
    -0.72
     Veg
    -0.72
    ãĤ¨ãĥ«
    -0.70
     Rasm
    -0.68
     prolet
    -0.66
     Slayer
    -0.66
    itans
    -0.66
    POSITIVE LOGITS
     probe
    1.92
     probes
    1.82
     investigating
    1.78
     investigation
    1.77
     investigations
    1.75
     probing
    1.72
     subpoen
    1.61
     subpoena
    1.60
     inquiry
    1.58
     investigate
    1.57
    Activations Density 0.535%

    No Known Activations