© 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. 8-RES-JB
    11. 11525
    Prev
    Next
    INDEX
    Explanations

    phrases and words related to winning, success, and victory

    oai_token-act-pair · gpt-3.5-turbo

    terms related to winning in competitive 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
    opian
    -0.75
    ensor
    -0.74
    ascript
    -0.71
    haar
    -0.70
    otropic
    -0.69
    heter
    -0.67
    anium
    -0.65
    aryn
    -0.65
    thening
    -0.64
    resent
    -0.64
    POSITIVE LOGITS
     streak
    1.19
     bidder
    1.04
     streaks
    1.01
    est
    0.77
     Eleven
    0.74
     candidate
    0.74
     percentages
    0.73
     combinations
    0.73
     combination
    0.72
     formula
    0.70
    Activations Density 0.033%

    No Known Activations