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. 18324
    Prev
    Next
    INDEX
    Explanations

    mentions of various foods and ingredients

    oai_token-act-pair · gpt-3.5-turbo

    the letter "p" in various contexts throughout the text

    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
     EDITION
    -0.81
     compe
    -0.76
     diplom
    -0.71
     horizont
    -0.70
    boarding
    -0.66
     resumes
    -0.64
     Geral
    -0.61
     directed
    -0.60
     differe
    -0.60
     juggling
    -0.59
    POSITIVE LOGITS
    udding
    1.39
    udd
    1.36
    uddle
    1.34
    anda
    1.25
    uddin
    1.24
    rawn
    1.24
    uffer
    1.22
    uffy
    1.21
    oodle
    1.20
    ixie
    1.19
    Activations Density 0.036%

    No Known Activations