© 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. 9-RES-JB
    11. 11734
    Prev
    Next
    INDEX
    Explanations

    references to or mentions of the football club Chelsea

    oai_token-act-pair · gpt-3.5-turbo

    references to "Chelsea," likely related to a sports team or individual associated with that name

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oppable
    -0.76
    abul
    -0.76
    utm
    -0.75
    tracking
    -0.71
    qqa
    -0.71
    lihood
    -0.70
    ertodd
    -0.70
    VIDIA
    -0.70
    haar
    -0.69
    ciating
    -0.69
    POSITIVE LOGITS
     Handler
    1.15
     Manning
    0.83
     FC
    0.77
     Harbour
    0.77
     Deposit
    0.73
    bies
    0.73
     beans
    0.68
     Pere
    0.68
     Clinton
    0.67
     Ladies
    0.66
    Activations Density 0.035%

    No Known Activations