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. 7-RES-JB
    6. 4491
    Prev
    Next
    INDEX
    Explanations

    keywords related to sports, especially football and baseball

    oai_token-act-pair · gpt-3.5-turbo

    terms related to football and sports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    shapeshifter
    -0.69
    antry
    -0.69
    cule
    -0.69
    lishes
    -0.68
    izabeth
    -0.68
     Borders
    -0.61
    ahime
    -0.60
     Ples
    -0.59
    ryn
    -0.59
    Elizabeth
    -0.58
    POSITIVE LOGITS
     stadiums
    1.04
     soccer
    1.02
     baseball
    1.01
     basketball
    1.01
     hockey
    1.00
     football
    1.00
     stadium
    0.94
     footballer
    0.92
     rugby
    0.89
     jerseys
    0.89
    Activations Density 0.450%

    No Known Activations