© 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. 1-RES-JB
    11. 9460
    Prev
    Next
    INDEX
    Explanations

    references to athletic activities or items

    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 @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sky
    -0.67
    к
    -0.67
    ppelin
    -0.65
    vironment
    -0.62
    enthal
    -0.62
    emb
    -0.62
     Bots
    -0.61
    SHIP
    -0.61
    erest
    -0.60
    oys
    -0.59
    POSITIVE LOGITS
     athletic
    1.21
     Athletic
    1.02
     athletics
    1.00
     apparel
    0.96
     footwear
    0.88
     basketball
    0.82
     physique
    0.81
     attire
    0.80
    querque
    0.79
     athlete
    0.79
    Activations Density 0.010%

    No Known Activations