Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 12-RES-JB
    6. 6998
    Prev
    Next
    INDEX
    Explanations

    information related to player rosters, injuries, competition, and team depth in sports

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

    terms related to team composition and player depth in sports

    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
     Wonderland
    -0.59
    DES
    -0.59
    tif
    -0.58
    realDonaldTrump
    -0.57
     platinum
    -0.56
     cinematic
    -0.55
     offline
    -0.53
     published
    -0.53
     eagerly
    -0.53
     eco
    -0.53
    POSITIVE LOGITS
    backer
    0.98
     linebacker
    0.94
     lineman
    0.94
     linemen
    0.91
     lineback
    0.90
     cornerback
    0.84
     rusher
    0.83
    tackle
    0.83
     linebackers
    0.80
     player
    0.80
    Activations Density 0.239%

    No Known Activations