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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 1357
    Prev
    Next
    INDEX
    Explanations

    words related to sports teams and players

    oai_token-act-pair · gpt-3.5-turbo

    references to specific sports teams and players

    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
    lishes
    -0.66
    izabeth
    -0.62
    shapeshifter
    -0.62
    antry
    -0.62
     flawless
    -0.58
     insane
    -0.58
    Elizabeth
    -0.57
    arine
    -0.56
     coma
    -0.55
    graded
    -0.54
    POSITIVE LOGITS
     stadiums
    0.92
     hockey
    0.89
     soccer
    0.89
     baseball
    0.86
     footballer
    0.86
     basketball
    0.83
     football
    0.82
     rugby
    0.80
    Fan
    0.79
     cricket
    0.76
    Activations Density 0.576%

    No Known Activations