© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11-RES-JB
    11. 18688
    Prev
    Next
    INDEX
    Explanations

    numerical patterns indicating durations of contracts

    oai_token-act-pair · gpt-3.5-turbo

    numerical values and durations related to contracts in sports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    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
     jealous
    -0.70
     Reaction
    -0.62
     rocking
    -0.60
     Appalach
    -0.60
    atican
    -0.58
     witchcraft
    -0.57
     Hast
    -0.57
     queues
    -0.57
    nces
    -0.57
    DERR
    -0.57
    POSITIVE LOGITS
    year
    1.22
    month
    1.08
    Month
    0.98
     year
    0.95
    season
    0.94
     month
    0.89
    game
    0.88
    Year
    0.88
    deal
    0.88
    offer
    0.87
    Activations Density 0.068%

    No Known Activations