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. 8-RES-JB
    6. 21658
    Prev
    Next
    INDEX
    Explanations

    communication actions such as sending messages, texts, letters, or emails

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include requests or communications involving the word "a"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Hispanic
    -0.65
    artifacts
    -0.65
     suicides
    -0.64
    align
    -0.63
    ARI
    -0.59
     unanim
    -0.59
    pire
    -0.58
     gripped
    -0.57
    utenberg
    -0.56
     clusters
    -0.56
    POSITIVE LOGITS
    ãĤ¹ãĥĪ
    0.80
    ãĥīãĥ©ãĤ´ãĥ³
    0.79
    gaard
    0.70
    ilts
    0.67
    ãĥ¥
    0.66
     broch
    0.65
    quez
    0.64
     opportunity
    0.63
     chance
    0.63
     gift
    0.63
    Activations Density 0.237%

    No Known Activations