© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 12015
    Prev
    Next
    INDEX
    Explanations

    references to sports championships

    oai_token-act-pair · gpt-3.5-turbo

    references to championship titles and sports achievements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Beh
    -0.71
    ttle
    -0.69
    asonic
    -0.69
    MpServer
    -0.69
    bass
    -0.68
    scope
    -0.67
    range
    -0.66
    arth
    -0.66
    details
    -0.66
    tan
    -0.66
    POSITIVE LOGITS
     Playoff
    0.87
     Rookie
    0.84
     Finals
    0.81
     trophy
    0.81
     MVP
    0.80
     accrued
    0.80
     Playoffs
    0.76
     medal
    0.76
     playoff
    0.75
     playoffs
    0.75
    Activations Density 0.103%

    No Known Activations