© 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. 6-RES-JB
    11. 20381
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to a person named Hogan

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Hogan" and references to Gawker

    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
    urized
    -0.80
    enza
    -0.77
    orescent
    -0.76
    aution
    -0.75
    uries
    -0.73
    aeda
    -0.73
    reen
    -0.72
    agogue
    -0.69
    reet
    -0.69
    ivism
    -0.69
    POSITIVE LOGITS
     Hogan
    1.19
     Suit
    0.75
     McMahon
    0.75
     Ic
    0.74
    ously
    0.70
    ball
    0.70
    lord
    0.70
     Gawker
    0.67
     WWF
    0.67
     Drake
    0.67
    Activations Density 0.043%

    No Known Activations