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. 7198
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Mis" followed by another character or characters

    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
     Schwarzenegger
    -0.65
     Ing
    -0.63
     JD
    -0.62
     Guardians
    -0.61
     Jehovah
    -0.60
    tc
    -0.59
     Carbuncle
    -0.59
     Bundy
    -0.58
     Aur
    -0.57
     Bernard
    -0.57
    POSITIVE LOGITS
    cellaneous
    1.55
    chief
    1.34
    ogyn
    1.31
    fortune
    1.30
    guided
    1.17
    cell
    1.15
    placed
    1.14
    beh
    1.11
    bah
    1.07
    leading
    1.06
    Activations Density 0.021%

    No Known Activations