Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 6-RES-JB
    6. 17994
    Prev
    Next
    INDEX
    Explanations

    descriptions related to physical movements and actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases that describe actions involving physical touch or interaction with objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     prosecutions
    -0.72
     prosecut
    -0.70
     credibility
    -0.65
     sectarian
    -0.65
     acron
    -0.62
     Cosponsors
    -0.61
     outsourcing
    -0.60
     McCarthy
    -0.60
     Architects
    -0.58
     philanthrop
    -0.58
    POSITIVE LOGITS
     stationary
    0.71
    entary
    0.66
     cursor
    0.65
     cue
    0.64
     choke
    0.59
    itu
    0.59
    iped
    0.58
    ipe
    0.58
     asleep
    0.58
     adjacent
    0.58
    Activations Density 0.921%

    No Known Activations