© 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. 4-RES-JB
    11. 4026
    Prev
    Next
    INDEX
    Explanations

    words related to athletics, sports, and physical fitness

    oai_token-act-pair · gpt-3.5-turbo

    terms related to athletics and sports

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

    No Comments

    Negative Logits
    ppelin
    -0.75
    oys
    -0.74
    orah
    -0.74
    later
    -0.70
    ainers
    -0.70
    enthal
    -0.68
    atche
    -0.67
    ectar
    -0.66
    vironment
    -0.65
    ered
    -0.64
    POSITIVE LOGITS
     athletic
    1.00
     Athletic
    0.89
     apparel
    0.88
     footwear
    0.85
     minded
    0.81
     commissions
    0.79
     trainers
    0.78
     trainer
    0.78
     fitness
    0.77
     athlete
    0.77
    Activations Density 0.006%

    No Known Activations