© 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. 11599
    Prev
    Next
    INDEX
    Explanations

    the surname "Steele" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific individual named Steele

    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
    ua
    -0.78
    rh
    -0.76
    rast
    -0.73
    hazard
    -0.71
    ensical
    -0.71
    assian
    -0.69
    outh
    -0.69
    erity
    -0.68
    isp
    -0.68
    asking
    -0.67
    POSITIVE LOGITS
    ved
    0.73
     Steele
    0.70
    Ste
    0.70
    iano
    0.69
    Rating
    0.67
    Feed
    0.65
     Nero
    0.65
    Chel
    0.64
    ving
    0.62
    lements
    0.61
    Activations Density 0.046%

    No Known Activations