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. 10-RES-JB
    6. 3991
    Prev
    Next
    INDEX
    Explanations

    conditional statements in sentences

    oai_token-act-pair · gpt-3.5-turbo

    conditional statements that discuss various scenarios or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tiny
    -0.68
    ãĤ´ãĥ³
    -0.66
    DragonMagazine
    -0.66
    Recipe
    -0.64
    cigarettes
    -0.64
    arious
    -0.63
    Contents
    -0.63
    verbal
    -0.62
    cffffcc
    -0.60
    gado
    -0.60
    POSITIVE LOGITS
     decides
    0.91
     wants
    0.88
     meets
    0.87
     aren
    0.85
     THEN
    0.81
     somebody
    0.81
     therefore
    0.80
     someone
    0.79
     refuses
    0.79
     weren
    0.79
    Activations Density 0.152%

    No Known Activations