© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 8-RES-JB
    11. 12945
    Prev
    Next
    INDEX
    Explanations

    words related to different sports teams, especially football and cricket

    oai_token-act-pair · gpt-3.5-turbo

    references to sports teams and players

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    ħĭ
    -0.75
    odox
    -0.73
    otics
    -0.73
    otropic
    -0.72
    MpServer
    -0.71
    rite
    -0.69
    ãĤ¢ãĥ«
    -0.69
    otic
    -0.67
    »Ĵ
    -0.66
    prison
    -0.66
    POSITIVE LOGITS
     extraord
    0.75
     Franch
    0.69
     Anthem
    0.68
    esses
    0.65
     desper
    0.64
     Manufact
    0.64
     Copyright
    0.64
     circa
    0.63
     Australia
    0.63
    ynthesis
    0.62
    Activations Density 0.382%

    No Known Activations