© 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. 6438
    Prev
    Next
    INDEX
    Explanations

    various instances of the word "decision."

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "decision."

    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
    icas
    -0.67
    aband
    -0.65
    ubric
    -0.65
    adata
    -0.64
     Colony
    -0.62
    uum
    -0.61
    uana
    -0.60
    rosse
    -0.59
    ience
    -0.58
     havoc
    -0.58
    POSITIVE LOGITS
     makers
    1.13
     maker
    0.96
    making
    0.92
    makers
    0.84
    maker
    0.79
     to
    0.72
     upholding
    0.71
     decision
    0.71
     taken
    0.71
     paralysis
    0.70
    Activations Density 0.047%

    No Known Activations