© 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. 10-RES-JB
    11. 3001
    Prev
    Next
    INDEX
    Explanations

    instances of the word "player" with varying levels of activation

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "player" in gaming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ories
    -0.73
    een
    -0.72
    DonaldTrump
    -0.71
    ournal
    -0.71
    ews
    -0.68
    enberg
    -0.67
    Truth
    -0.66
    ynski
    -0.64
     Downs
    -0.63
    azo
    -0.63
    POSITIVE LOGITS
    Unknown
    1.02
    base
    0.92
    Players
    0.86
    Alias
    0.82
     Piano
    0.82
    PLAY
    0.82
    player
    0.81
    players
    0.80
    testing
    0.80
     avatar
    0.79
    Activations Density 0.043%

    No Known Activations