© 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. 11-RES-JB
    11. 4985
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "straw" with various degrees of relevance

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "straw" or references to "Dana" and places associated with Newcastle

    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
    izations
    -0.98
    acca
    -0.97
    ized
    -0.96
    izable
    -0.95
    ties
    -0.93
    ocation
    -0.85
    ization
    -0.84
    ations
    -0.84
    olog
    -0.83
    istic
    -0.83
    POSITIVE LOGITS
    e
    0.77
     Nunes
    0.74
    sburg
    0.73
    s
    0.71
     Mew
    0.68
     Jets
    0.66
    weights
    0.66
    issance
    0.66
     Clover
    0.65
     Scully
    0.64
    Activations Density 0.127%

    No Known Activations