© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 10312
    Prev
    Next
    INDEX
    Explanations

    phrases related to the sports industry and potentially specific individuals like athletes

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals, particularly names in sports contexts

    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
    estern
    -0.70
    rooms
    -0.66
    erald
    -0.66
    tnc
    -0.65
    iculty
    -0.65
    advertisement
    -0.63
    olves
    -0.63
    ilight
    -0.63
    IRED
    -0.63
    ests
    -0.62
    POSITIVE LOGITS
     Stur
    1.40
    ftime
    0.83
    pling
    0.71
     Sta
    0.71
     GER
    0.70
     streng
    0.69
    gren
    0.69
    sel
    0.68
    lund
    0.66
    rences
    0.66
    Activations Density 0.019%

    No Known Activations