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. 22907
    Prev
    Next
    INDEX
    Explanations

    descriptions of specific actions in sports

    oai_token-act-pair · gpt-3.5-turbo

    verbs related to movement and physical actions

    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
    cius
    -0.63
     demographic
    -0.62
    forums
    -0.60
     settlements
    -0.59
     demographics
    -0.58
    ctors
    -0.58
    Edited
    -0.57
     regard
    -0.56
     respects
    -0.56
    Ranked
    -0.56
    POSITIVE LOGITS
     goalkeeper
    0.83
    edin
    0.83
     teammate
    0.81
     fingert
    0.81
     calmly
    0.80
     volley
    0.80
     confidently
    0.77
     awkwardly
    0.76
     himself
    0.73
     onto
    0.73
    Activations Density 0.156%

    No Known Activations