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. 19960
    Prev
    Next
    INDEX
    Explanations

    instances where the document provides examples or explanations

    oai_token-act-pair · gpt-3.5-turbo

    words that involve a specific format or structure, particularly the presence of letters 'e' and 'g' in specific contexts

    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
    theless
    -0.64
    SHARE
    -0.54
    '';
    -0.51
    adobe
    -0.50
    LOCK
    -0.49
    TEXTURE
    -0.49
    cffffcc
    -0.48
     rightfully
    -0.48
    COLOR
    -0.47
    CLOSE
    -0.47
    POSITIVE LOGITS
    .,
    1.73
    .:
    1.45
    .;
    1.24
    .).
    1.14
    .),
    1.11
    .,"
    1.05
    .):
    1.04
    .?
    1.01
    .-
    0.95
    ./
    0.90
    Activations Density 0.025%

    No Known Activations