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. 17926
    Prev
    Next
    INDEX
    Explanations

    phrases related to options or possibilities

    oai_token-act-pair · gpt-3.5-turbo

    questions or conditional phrases indicating possibilities

    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
    then
    -0.66
    / 
    -0.62
    estamp
    -0.61
    ords
    -0.61
     Prairie
    -0.60
     then
    -0.59
     THEN
    -0.59
     WATCHED
    -0.58
    onds
    -0.55
    ogun
    -0.54
    POSITIVE LOGITS
     simply
    1.16
     outright
    1.08
     merely
    1.04
     just
    0.92
    abouts
    0.92
     alternatively
    0.92
     altogether
    0.92
     downright
    0.90
    Else
    0.88
     unlucky
    0.79
    Activations Density 0.286%

    No Known Activations