© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 7-RES-JB
    11. 21094
    Prev
    Next
    INDEX
    Explanations

    instances where some task or activity has been completed

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "completed" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    maid
    -0.73
    gypt
    -0.70
    lua
    -0.67
    pter
    -0.65
    ung
    -0.63
    dh
    -0.62
    spr
    -0.61
    hot
    -0.61
    iewicz
    -0.59
    bour
    -0.58
    POSITIVE LOGITS
    issance
    0.90
    teness
    0.90
    TAIN
    0.83
     completion
    0.75
     feasibility
    0.73
     captcha
    0.71
    ances
    0.71
    rehensive
    0.69
     crossings
    0.69
    missions
    0.67
    Activations Density 0.036%

    No Known Activations