© 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. 0-RES-JB
    11. 1353
    Prev
    Next
    INDEX
    Explanations

    references to a specific soccer team, likely "FC"

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific entity or brand, particularly "FC."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pers
    -0.65
     timet
    -0.64
     Betsy
    -0.63
     ethn
    -0.63
     occupations
    -0.62
     rh
    -0.61
     repeats
    -0.61
     skeletons
    -0.61
     Milo
    -0.60
     Rik
    -0.60
    POSITIVE LOGITS
    FC
    4.38
     FC
    1.94
    fc
    1.77
    FD
    1.51
    FP
    1.43
    FS
    1.42
    HC
    1.38
    FF
    1.37
    FT
    1.37
    EC
    1.35
    Activations Density 0.012%

    No Known Activations