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. 10-RES-JB
    6. 22614
    Prev
    Next
    INDEX
    Explanations

    movement-related activities or actions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to physical movements and exercise

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Journals
    -0.88
     UNHCR
    -0.81
     indemn
    -0.74
    Reviewer
    -0.73
    actionDate
    -0.72
     Funding
    -0.72
     sourcing
    -0.69
     Financial
    -0.69
     Insurance
    -0.67
    greSQL
    -0.67
    POSITIVE LOGITS
     performed
    1.24
     chore
    1.09
     mastered
    1.01
     repertoire
    0.98
     involving
    0.97
     technique
    0.96
     routines
    0.95
     perfected
    0.94
     practiced
    0.93
     routine
    0.93
    Activations Density 0.297%

    No Known Activations