© 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. 9-RES-JB
    11. 17453
    Prev
    Next
    INDEX
    Explanations

    references to individuals being named to various sports teams or receiving awards

    oai_token-act-pair · gpt-3.5-turbo

    references to sports achievements and accolades

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    entimes
    -0.91
    orce
    -0.77
     democrat
    -0.72
     gent
    -0.67
     pend
    -0.67
    tale
    -0.66
     peacefully
    -0.64
    iour
    -0.63
     umb
    -0.61
    oise
    -0.59
    POSITIVE LOGITS
     finalists
    0.94
     rosters
    0.91
     STATS
    0.87
    Draft
    0.87
     XI
    0.85
     roster
    0.85
     Rookie
    0.81
    PHOTOS
    0.81
     captains
    0.81
     draft
    0.80
    Activations Density 0.214%

    No Known Activations