© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 7-RES-JB
    11. 17123
    Prev
    Next
    INDEX
    Explanations

    actions involving physical movements, particularly ones related to arms and hands

    oai_token-act-pair · gpt-3.5-turbo

    actions involving physical contact or impact

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CLUS
    -0.87
     suites
    -0.77
     conformity
    -0.76
    undown
    -0.68
     Bast
    -0.68
     redundancy
    -0.67
    eming
    -0.66
     pandemonium
    -0.65
    fam
    -0.65
    士
    -0.65
    POSITIVE LOGITS
     gently
    1.07
     fingers
    1.01
     fingertips
    0.99
     angled
    0.97
    tip
    0.95
     paddle
    0.92
    button
    0.91
     downwards
    0.91
    tips
    0.90
     pressed
    0.90
    Activations Density 0.351%

    No Known Activations