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. 19942
    Prev
    Next
    INDEX
    Explanations

    promotional phrases and technical terms related to products and services

    oai_token-act-pair · gpt-3.5-turbo

    references to contemporary political issues

    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
     tack
    -0.94
     paddle
    -0.93
     Payton
    -0.92
     tow
    -0.80
     Bentley
    -0.79
     Carroll
    -0.79
     Webb
    -0.76
     Pepper
    -0.74
     ballet
    -0.74
    âĸĵ
    -0.73
    POSITIVE LOGITS
     Gen
    2.43
    Gen
    2.23
     gen
    1.97
     GEN
    1.96
    gen
    1.77
    GEN
    1.67
     Generation
    1.63
     Genetics
    1.51
    Gener
    1.50
     Genetic
    1.47
    Activations Density 0.143%

    No Known Activations