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. 6-RES-JB
    6. 13393
    Prev
    Next
    INDEX
    Explanations

    mentions of fans

    oai_token-act-pair · gpt-3.5-turbo

    references to fans and their experiences or emotions in relation to sports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nom
    -0.76
    lished
    -0.72
    redo
    -0.66
    ered
    -0.66
    ateral
    -0.64
    dit
    -0.64
    vet
    -0.63
    Chain
    -0.62
    Published
    -0.61
     batch
    -0.61
    POSITIVE LOGITS
     boo
    0.98
     cheering
    0.98
     stadiums
    0.91
     chanting
    0.88
    verson
    0.84
     Atmosp
    0.83
    atics
    0.82
     chanted
    0.82
    haw
    0.81
    boys
    0.79
    Activations Density 0.057%

    No Known Activations