© 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. 1-RES-JB
    11. 13511
    Prev
    Next
    INDEX
    Explanations

    words related to taking action or responding

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "taken" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    heter
    -0.78
    RP
    -0.73
     gol
    -0.69
    inals
    -0.64
    ocr
    -0.63
    lus
    -0.62
    posium
    -0.62
    ptive
    -0.62
    HB
    -0.61
    FG
    -0.60
    POSITIVE LOGITS
    aken
    1.05
    atche
    0.87
    edIn
    0.82
    aukee
    0.81
    nington
    0.76
    apeake
    0.71
    ãĥĥãĥĪ
    0.68
    mares
    0.67
    wright
    0.67
    lishing
    0.67
    Activations Density 0.008%

    No Known Activations