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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 3256
    Prev
    Next
    INDEX
    Explanations

    mentions of winning or victory

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "won" and its variants, which indicate victories or success

    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
    senal
    -0.64
    heter
    -0.62
    tan
    -0.62
     scanner
    -0.61
    opter
    -0.60
     sket
    -0.60
    tar
    -0.59
     trolls
    -0.58
    erous
    -0.58
    ria
    -0.58
    POSITIVE LOGITS
    't
    0.94
    nings
    0.87
     championships
    0.85
     streak
    0.82
     Rookie
    0.82
     outright
    0.80
    ced
    0.79
     streaks
    0.79
     MVP
    0.76
    throp
    0.76
    Activations Density 0.054%

    No Known Activations