© 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. 10-RES-JB
    11. 15999
    Prev
    Next
    INDEX
    Explanations

    information related to athlete career milestones or accomplishments

    oai_token-act-pair · gpt-3.5-turbo

    information related to a player's career milestones and achievements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GOP
    -0.84
    Chuck
    -0.78
    Larry
    -0.75
    cius
    -0.74
    pmwiki
    -0.73
     Thro
    -0.73
     Kathy
    -0.72
    avanaugh
    -0.71
     nonpartisan
    -0.70
     goddamn
    -0.70
    POSITIVE LOGITS
     Tottenham
    1.24
     Newcastle
    1.23
     Sunderland
    1.21
     footballer
    1.20
     Everton
    1.16
     Bundesliga
    1.16
     Southampton
    1.15
     Cardiff
    1.11
     Liverpool
    1.11
    ottenham
    1.10
    Activations Density 0.408%

    No Known Activations