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. 2505
    Prev
    Next
    INDEX
    Explanations

    text related to physical actions or movements, particularly involving clapping or striking

    oai_token-act-pair · gpt-3.5-turbo

    words related to clapping or similar actions

    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
    CLA
    -0.75
     unexpl
    -0.72
     commons
    -0.69
    ãĥ´
    -0.68
    Ͻ
    -0.67
     DRAG
    -0.66
    LV
    -0.66
    ãĥĨãĤ£
    -0.66
    schild
    -0.65
     Vaults
    -0.63
    POSITIVE LOGITS
    ulous
    0.82
    itiveness
    0.80
    */(
    0.79
    ulence
    0.79
    idity
    0.77
    hedral
    0.76
    hemy
    0.75
    ularity
    0.74
    nces
    0.73
    icles
    0.73
    Activations Density 0.035%

    No Known Activations