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. 7206
    Prev
    Next
    INDEX
    Explanations

    instances of the word "apply" within different contexts

    oai_token-act-pair · gpt-3.5-turbo
    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
    watching
    -0.70
    footed
    -0.66
    ument
    -0.64
    nia
    -0.64
    hoff
    -0.63
    birds
    -0.62
    aired
    -0.62
    owship
    -0.62
    acters
    -0.61
    bill
    -0.60
    POSITIVE LOGITS
     pressure
    0.95
     brakes
    0.72
     sunscreen
    0.71
    ogen
    0.68
     rigorous
    0.67
    arate
    0.65
     liber
    0.65
     lessons
    0.64
     lipstick
    0.64
     mathematical
    0.63
    Activations Density 0.045%

    No Known Activations