Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 14206
    Prev
    Next
    INDEX
    Explanations

    names of famous athletes and sports personalities

    oai_token-act-pair · gpt-3.5-turbo

    mentions of prominent athletes and figures in sports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    é¾
    -0.75
    usra
    -0.71
    unal
    -0.70
    ourcing
    -0.69
    umbn
    -0.65
    ned
    -0.65
    aughters
    -0.65
    aught
    -0.64
    icycle
    -0.64
    iltr
    -0.63
    POSITIVE LOGITS
     Messi
    1.26
     Ronaldo
    0.94
     Guardiola
    0.91
    otle
    0.87
    eta
    0.80
    etz
    0.79
     TAMADRA
    0.70
    ysc
    0.69
    eters
    0.68
    zzi
    0.68
    Activations Density 0.009%

    No Known Activations