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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 1-RES-JB
    6. 13663
    Prev
    Next
    INDEX
    Explanations

    names associated with sports, particularly those related to hockey

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals, particularly those related to sports and public figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    acity
    -0.86
    ators
    -0.79
    rums
    -0.74
    ources
    -0.70
    Charges
    -0.70
    Federal
    -0.68
    ivities
    -0.68
    $$$$
    -0.67
    rum
    -0.66
    ivity
    -0.66
    POSITIVE LOGITS
     Howe
    1.49
     mosqu
    0.84
    zeb
    0.82
    elin
    0.81
     Downs
    0.80
    vernment
    0.76
     Isles
    0.74
    hole
    0.72
    worms
    0.71
    llers
    0.71
    Activations Density 0.013%

    No Known Activations