© 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. 9981
    Prev
    Next
    INDEX
    Explanations

    statements about the number of games played by athletes

    oai_token-act-pair · gpt-3.5-turbo

    references to the number of games played in a sports context

    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
    NRS
    -0.73
    Panel
    -0.69
    sonian
    -0.64
    ariat
    -0.60
    =-=-=-=-=-=-=-=-
    -0.56
     Mood
    -0.56
    idden
    -0.55
     wedge
    -0.55
    Exit
    -0.54
     Agenda
    -0.54
    POSITIVE LOGITS
     professionally
    0.94
     for
    0.89
     colleg
    0.88
     alongside
    0.85
     stint
    0.81
     playing
    0.80
     with
    0.78
     coaching
    0.76
    uper
    0.75
     collegiate
    0.75
    Activations Density 0.241%

    No Known Activations