© 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. 23748
    Prev
    Next
    INDEX
    Explanations

    dates and ordinal numbers

    oai_token-act-pair · gpt-3.5-turbo

    ordinal numbers and their associated formats

    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
    etting
    -0.68
    enne
    -0.67
    recy
    -0.66
    mbuds
    -0.66
    advertisement
    -0.64
    ptin
    -0.64
    kens
    -0.62
    staking
    -0.61
    ffee
    -0.61
    bub
    -0.60
    POSITIVE LOGITS
     Amendment
    1.08
     Floor
    1.00
    ousand
    0.99
     Avenue
    0.98
     Degree
    0.98
     Century
    0.98
     Annual
    0.97
     Anniversary
    0.97
     percentile
    0.96
     Circuit
    0.94
    Activations Density 0.041%

    No Known Activations