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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11-RES-JB
    11. 17070
    Prev
    Next
    INDEX
    Explanations

    mentions of specific years or periods of time in a person's career

    oai_token-act-pair · gpt-3.5-turbo

    references to rookie seasons and performance metrics in sports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     thinkers
    -0.76
     GOODMAN
    -0.75
     presenter
    -0.69
    dogs
    -0.68
     Guests
    -0.63
     terr
    -0.61
     kW
    -0.61
     thinker
    -0.59
     kindred
    -0.59
    seekers
    -0.58
    POSITIVE LOGITS
     stint
    1.17
     career
    1.11
     collegiate
    1.04
     NFL
    1.01
     CFL
    0.99
     tenure
    0.98
     rookie
    0.97
     seasons
    0.96
     season
    0.96
     NBA
    0.96
    Activations Density 0.169%

    No Known Activations