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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 0-RES-JB
    6. 5639
    Prev
    Next
    INDEX
    Explanations

    the word "ho" with varying levels of activation

    oai_token-act-pair · gpt-3.5-turbo

    the word "ho" in various contexts and forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Zig
    -0.70
     result
    -0.68
     Flavoring
    -0.66
     divorce
    -0.66
     resolutions
    -0.64
     Sheldon
    -0.64
     Calais
    -0.64
     Dent
    -0.64
     Silver
    -0.63
     results
    -0.60
    POSITIVE LOGITS
    ho
    4.65
    Ho
    1.74
    hoe
    1.68
    hi
    1.62
    HO
    1.61
    hops
    1.57
    hop
    1.57
    hu
    1.55
    ha
    1.47
    hin
    1.41
    Activations Density 0.010%

    No Known Activations