© 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. 19601
    Prev
    Next
    INDEX
    Explanations

    words related to racing events

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the term "race" and its context throughout the document

    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
    olia
    -0.91
    osis
    -0.82
    tymology
    -0.78
    berra
    -0.77
    ogle
    -0.75
    obar
    -0.75
    ollywood
    -0.75
    iar
    -0.75
    argon
    -0.74
    amas
    -0.74
    POSITIVE LOGITS
    course
    1.23
    horse
    1.02
    bike
    0.93
    cars
    0.92
     Races
    0.90
     race
    0.85
     races
    0.84
    car
    0.82
     racing
    0.81
     weekends
    0.78
    Activations Density 0.019%

    No Known Activations