© 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. 10194
    Prev
    Next
    INDEX
    Explanations

    keywords related to political races or election campaigns

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "race" in various contexts

    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
    ushima
    -0.88
    iar
    -0.72
    osis
    -0.71
    ipedia
    -0.70
    alt
    -0.69
    berra
    -0.68
    omy
    -0.68
    ailability
    -0.67
    SOURCE
    -0.67
    omical
    -0.67
    POSITIVE LOGITS
    course
    1.13
    eering
    0.96
    horse
    0.87
    manship
    0.86
    running
    0.75
    runners
    0.74
     races
    0.74
    smith
    0.73
    worthiness
    0.73
     pitted
    0.73
    Activations Density 0.015%

    No Known Activations