© 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. 7-RES-JB
    11. 3874
    Prev
    Next
    INDEX
    Explanations

    names of athletes

    oai_token-act-pair · gpt-3.5-turbo

    names of professional athletes and their performance metrics

    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
    netflix
    -0.83
    words
    -0.81
    polit
    -0.80
    DragonMagazine
    -0.75
     Cosponsors
    -0.75
    bara
    -0.71
    sylv
    -0.70
    uscript
    -0.70
    sth
    -0.69
    axis
    -0.69
    POSITIVE LOGITS
     Rodgers
    0.97
     Westbrook
    0.97
     undrafted
    0.96
     Manziel
    0.95
     rookie
    0.95
     Wiggins
    0.93
     Wade
    0.91
     PHI
    0.91
     Robinson
    0.91
     Matthews
    0.91
    Activations Density 0.184%

    No Known Activations