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. 10-RES-JB
    6. 23567
    Prev
    Next
    INDEX
    Explanations

    words related to bodily movements and physical actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating actions or movements directed towards something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    updated
    -0.82
    uania
    -0.67
    published
    -0.67
    Week
    -0.65
     Updated
    -0.63
    Published
    -0.62
    fol
    -0.61
    Originally
    -0.61
    packing
    -0.60
    ivil
    -0.58
    POSITIVE LOGITS
     simulate
    1.34
     accommodate
    1.25
     signify
    1.23
     facilitate
    1.18
     avoid
    1.18
     reveal
    1.17
     relieve
    1.15
     prevent
    1.14
     minimize
    1.14
     ensure
    1.13
    Activations Density 0.146%

    No Known Activations