Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 5211
    Prev
    Next
    INDEX
    Explanations

    timestamps relative to movement or physical activity

    oai_token-act-pair · gpt-3.5-turbo

    various forms of the word "movement."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zona
    -0.72
    ihil
    -0.72
    zan
    -0.68
    unts
    -0.68
    oys
    -0.66
    nect
    -0.66
    GE
    -0.65
    ãĤ©
    -0.65
    odium
    -0.63
    ju
    -0.62
    POSITIVE LOGITS
     movements
    0.93
     movement
    0.90
     motions
    0.86
    peed
    0.82
    letal
    0.75
    able
    0.75
     motion
    0.73
     disorder
    0.73
     direction
    0.72
     sickness
    0.72
    Activations Density 0.040%

    No Known Activations