© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 21081
    Prev
    Next
    INDEX
    Explanations

    mentions of the Sundance Film Festival

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the Sundance Film Festival and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     posit
    -0.78
     Confederation
    -0.77
    itably
    -0.67
     impe
    -0.67
     Hil
    -0.64
     association
    -0.64
     Hazard
    -0.62
     logger
    -0.60
     HIP
    -0.59
    manship
    -0.59
    POSITIVE LOGITS
    ance
    1.16
    ancer
    1.12
    owner
    1.12
    own
    1.02
    ragon
    1.00
    arb
    1.00
    owners
    1.00
    evil
    0.98
    ered
    0.97
    inav
    0.97
    Activations Density 0.068%

    No Known Activations