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. 5-RES-JB
    6. 24303
    Prev
    Next
    INDEX
    Explanations

    references to sports officials, specifically referees

    oai_token-act-pair · gpt-3.5-turbo

    references to referees in sports contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Sea
    -0.72
    izoph
    -0.71
    ocobo
    -0.70
    stem
    -0.67
    yles
    -0.66
    VILLE
    -0.65
     VIDEOS
    -0.65
     Horses
    -0.65
    ESE
    -0.64
    tom
    -0.63
    POSITIVE LOGITS
    eree
    1.05
     referees
    0.94
     referee
    0.94
    esses
    0.82
     stopp
    0.78
     rigged
    0.76
     examiner
    0.75
    ÃŃa
    0.73
    bage
    0.70
    iquette
    0.70
    Activations Density 0.034%

    No Known Activations