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. 11-RES-JB
    6. 16227
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific person named "Comey" and actions related to him

    oai_token-act-pair · gpt-3.5-turbo

    mentions of James Comey and related figures in a political context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AIDS
    -0.70
    loading
    -0.70
    liga
    -0.70
     Mond
    -0.70
    ¥µ
    -0.69
    Tu
    -0.67
    lord
    -0.65
     Fiji
    -0.65
    icons
    -0.65
    load
    -0.64
    POSITIVE LOGITS
     testified
    1.19
     memos
    1.02
     testifying
    1.02
    agher
    0.88
     Comey
    0.88
     briefings
    0.86
     exoner
    0.85
     testimony
    0.85
     briefed
    0.84
     testify
    0.83
    Activations Density 0.045%

    No Known Activations