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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 9-RES-JB
    11. 4813
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to a football team (possibly the New England Patriots) and individuals associated with it

    oai_token-act-pair · gpt-3.5-turbo

    references to the Brady and Patriots football teams

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sie
    -0.80
    yrinth
    -0.78
    ĺħ
    -0.70
    undai
    -0.68
    oths
    -0.66
    ORE
    -0.66
    erness
    -0.65
     ponies
    -0.65
    ouri
    -0.65
    oras
    -0.65
    POSITIVE LOGITS
    ichick
    0.95
    igham
    0.82
     Belichick
    0.81
    ica
    0.78
    icas
    0.76
    riots
    0.72
    icans
    0.71
    backer
    0.71
    igue
    0.70
    abl
    0.69
    Activations Density 0.063%

    No Known Activations