© 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. 16303
    Prev
    Next
    INDEX
    Explanations

    I couldn't find a consistent pattern for Neuron 4 based on the provided activations

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of dates and events

    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
     millenn
    -0.91
    senal
    -0.80
    isSpecial
    -0.79
    ãĤ´ãĥ³
    -0.74
     streng
    -0.73
     redes
    -0.73
     conclud
    -0.71
     gobl
    -0.71
     referen
    -0.69
     rall
    -0.68
    POSITIVE LOGITS
    ilet
    0.83
    cks
    0.76
    aya
    0.74
    cher
    0.73
    ECK
    0.72
    ec
    0.71
    Ä
    0.70
    urger
    0.69
    Chest
    0.67
     Shaw
    0.67
    Activations Density 0.176%

    No Known Activations