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. 0-RES-JB
    6. 21988
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical body parts, particularly hands

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "hands" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pton
    -0.75
    elta
    -0.70
    Section
    -0.68
     Topic
    -0.65
    SPONSORED
    -0.65
    prop
    -0.61
     SECTION
    -0.61
    shown
    -0.60
    Äį
    -0.60
    ENN
    -0.59
    POSITIVE LOGITS
     hands
    4.11
    hands
    2.55
     Hands
    2.44
     paws
    2.06
     hand
    1.80
     wrists
    1.78
     palms
    1.78
     fingers
    1.77
     fists
    1.74
     fingertips
    1.71
    Activations Density 0.022%

    No Known Activations