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. 11-RES-JB
    6. 8691
    Prev
    Next
    INDEX
    Explanations

    verbs related to movement on foot

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "walk" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Saud
    -0.65
    iller
    -0.64
    encies
    -0.64
    orious
    -0.63
    iler
    -0.62
    rent
    -0.60
    nant
    -0.60
    mal
    -0.60
    etric
    -0.59
    iling
    -0.58
    POSITIVE LOGITS
     away
    1.08
    through
    1.01
     upright
    0.92
     confidently
    0.88
     uphill
    0.86
     brisk
    0.86
     into
    0.85
     ginger
    0.84
    about
    0.83
     awa
    0.83
    Activations Density 0.048%

    No Known Activations