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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 3-RES-JB
    11. 16331
    Prev
    Next
    INDEX
    Explanations

    references to the Winter Olympics event held in Sochi and mentions of the hockey player Sidney Crosby

    oai_token-act-pair · gpt-3.5-turbo

    references to the Sochi Olympics and significant players like Sidney Crosby

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    isition
    -0.79
    istrate
    -0.67
    PDATE
    -0.67
    cknow
    -0.65
    isitions
    -0.64
    lance
    -0.62
    bidden
    -0.61
    MpServer
    -0.61
     cane
    -0.61
    cknowled
    -0.60
    POSITIVE LOGITS
     Crosby
    1.20
    algia
    0.82
    sburgh
    0.81
    tor
    0.78
    achu
    0.76
     Chong
    0.76
    Ñĥ
    0.75
     Sochi
    0.73
     Schr
    0.71
    bral
    0.71
    Activations Density 0.018%

    No Known Activations