© 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. 12-RES-JB
    11. 3719
    Prev
    Next
    INDEX
    Explanations

    names of football players

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    references to specific players and their performance in sports contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
     Anchorage
    -0.83
     Triumph
    -0.73
     Intercept
    -0.72
     Nationals
    -0.72
     DSL
    -0.72
     CPC
    -0.71
     Progressive
    -0.69
     Customs
    -0.68
     unsupported
    -0.67
     Dominion
    -0.67
    POSITIVE LOGITS
    ilic
    1.14
    azard
    1.10
    ardy
    1.10
    eman
    1.07
    iago
    1.06
    lopp
    1.05
    ventus
    1.05
    ortmund
    1.04
    letico
    1.03
    oleon
    1.02
    Activations Density 0.076%

    No Known Activations