© 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 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. 11-RES-JB
    11. 18441
    Prev
    Next
    INDEX
    Explanations

    names of individuals in sports

    oai_token-act-pair · gpt-3.5-turbo

    numerical identifiers and player stats in sports contexts

    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
     disadvant
    -0.70
     Warden
    -0.68
     overriding
    -0.67
     Slave
    -0.67
     paranoia
    -0.66
     bystand
    -0.64
    Issue
    -0.64
     mockery
    -0.64
     Advertisement
    -0.62
     Carn
    -0.61
    POSITIVE LOGITS
     underwent
    1.24
     joins
    1.23
     signed
    1.12
     joined
    1.11
     averaged
    1.10
     participated
    1.06
     rejo
    1.05
     debuted
    1.04
     played
    1.03
     scored
    1.03
    Activations Density 0.188%

    No Known Activations