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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 16827
    Prev
    Next
    INDEX
    Explanations

    phrases mentioning the word "with" followed by various contexts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "with" indicating collaboration or association

    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
    fair
    -0.79
    working
    -0.71
    chuk
    -0.67
    shire
    -0.66
    borgh
    -0.64
    here
    -0.62
    Reilly
    -0.62
    sov
    -0.61
    liner
    -0.61
    mans
    -0.60
    POSITIVE LOGITS
    drawn
    0.86
    draw
    0.79
     Views
    0.74
     caveats
    0.74
     Radeon
    0.74
     annotations
    0.73
     Recipes
    0.73
     lyrics
    0.73
     guiActiveUnfocused
    0.71
    cloneembedreportprint
    0.69
    Activations Density 0.031%

    No Known Activations