© 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. 20478
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to actions or directives

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "action" in various contexts

    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
    gling
    -0.68
    YL
    -0.62
    thening
    -0.62
    aez
    -0.61
    mining
    -0.61
    KER
    -0.60
     Affairs
    -0.60
    Äį
    -0.57
    gins
    -0.57
    arton
    -0.56
    POSITIVE LOGITS
    able
    0.95
    ivated
    0.93
     Replay
    0.83
     verbs
    0.81
    quit
    0.81
    ives
    0.80
    figure
    0.79
     hero
    0.79
    igraph
    0.76
    iveness
    0.75
    Activations Density 0.050%

    No Known Activations