© 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. 8-RES-JB
    11. 18536
    Prev
    Next
    INDEX
    Explanations

    mentions of the city "Winnipeg"

    oai_token-act-pair · gpt-3.5-turbo

    references to Winnipeg and its significance in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ridor
    -0.93
     externalToEVAOnly
    -0.84
    relation
    -0.79
    amount
    -0.79
    pee
    -0.76
    byn
    -0.76
    chell
    -0.74
    oute
    -0.74
    IOR
    -0.71
    onies
    -0.69
    POSITIVE LOGITS
    s
    0.88
    theless
    0.82
    ipeg
    0.76
    strings
    0.71
    uration
    0.70
     Jets
    0.69
    ers
    0.69
    Tang
    0.67
    swe
    0.67
    shire
    0.66
    Activations Density 0.066%

    No Known Activations