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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 14139
    Prev
    Next
    INDEX
    Explanations

    words related to movement and physical activity

    oai_token-act-pair · gpt-3.5-turbo

    references to motion in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sqor
    -0.73
    scl
    -0.72
    dds
    -0.71
    rosso
    -0.70
    arding
    -0.69
    aez
    -0.68
    é¾įå
    -0.68
    allery
    -0.66
    azine
    -0.64
    initions
    -0.63
    POSITIVE LOGITS
     motion
    1.19
    motion
    1.09
     Motion
    1.06
    Motion
    0.98
     motions
    0.93
     sickness
    0.89
    immune
    0.81
     blur
    0.79
    Animation
    0.76
    less
    0.70
    Activations Density 0.007%

    No Known Activations