© 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. 2740
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to a specific individual named Trey Gowdy and terms related to gaming

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals, particularly Trey Gowdy, and contexts related to gaming

    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
    paralle
    -0.76
    elope
    -0.67
    inguishable
    -0.67
    inct
    -0.65
     pilgr
    -0.65
    orph
    -0.63
    oys
    -0.62
    ciples
    -0.62
    usions
    -0.62
    etheus
    -0.61
    POSITIVE LOGITS
    vernment
    0.92
    yip
    0.79
    bye
    0.78
    -+-+
    0.77
     Pengu
    0.77
    RAFT
    0.77
    irlfriend
    0.77
    allery
    0.73
    ghazi
    0.73
    dinand
    0.71
    Activations Density 0.029%

    No Known Activations