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. 10596
    Prev
    Next
    INDEX
    Explanations

    ingredients and cooking instructions in a recipe-like format

    oai_token-act-pair · gpt-3.5-turbo

    fractional measurements or ratios typically used in recipes

    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
     Muse
    -0.68
     Cele
    -0.68
     orphan
    -0.68
     broker
    -0.67
     diagn
    -0.65
    chnology
    -0.65
     endorsements
    -0.63
     seism
    -0.63
     EB
    -0.62
     glitches
    -0.61
    POSITIVE LOGITS
    4
    1.50
    2
    1.38
    3
    1.33
    8
    1.31
    16
    1.16
    fourth
    1.12
    5
    1.08
    ħ
    1.08
    6
    1.08
    144
    1.04
    Activations Density 0.019%

    No Known Activations