© 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. 10-RES-JB
    11. 17292
    Prev
    Next
    INDEX
    Explanations

    mentions of events or locations related to the Sundance Film Festival

    oai_token-act-pair · gpt-3.5-turbo

    references to the Sundance Film Festival

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     posit
    -0.84
    itably
    -0.73
    tsky
    -0.72
     Confederation
    -0.71
     clipboard
    -0.64
     detector
    -0.64
     carriers
    -0.62
    ··
    -0.62
     relat
    -0.61
     impe
    -0.60
    POSITIVE LOGITS
    ance
    1.01
    ancer
    0.95
    ered
    0.95
    ecided
    0.94
    erella
    0.93
    inav
    0.92
    rum
    0.92
    owner
    0.92
    arb
    0.92
    ry
    0.89
    Activations Density 0.035%

    No Known Activations