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. 11822
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "hands"

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "hands," often in contexts related to possession, control, or interaction

    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
    ļéĨĴ
    -0.72
     Corrections
    -0.67
     Sec
    -0.65
     Neigh
    -0.65
     Prediction
    -0.64
    vell
    -0.63
    Marginal
    -0.62
     Savings
    -0.62
     Opportun
    -0.61
    MSN
    -0.61
    POSITIVE LOGITS
    maid
    1.17
    pring
    1.10
    chool
    1.00
    handed
    0.99
    creen
    0.87
    hander
    0.87
     paws
    0.86
    shake
    0.84
    chu
    0.82
    picked
    0.82
    Activations Density 0.018%

    No Known Activations