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. 10-RES-JB
    6. 1970
    Prev
    Next
    INDEX
    Explanations

    examples indicating the application of a concept or principle

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the letter 'g' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     unpre
    -0.64
    theless
    -0.64
     unconventional
    -0.59
    manship
    -0.58
     perfectly
    -0.57
     successive
    -0.57
     ages
    -0.56
     tranquil
    -0.56
    avorite
    -0.55
     discour
    -0.55
    POSITIVE LOGITS
    .,
    1.75
    .:
    1.26
    .;
    1.20
    .).
    1.15
    .),
    1.11
    .,"
    1.01
    .):
    1.00
    .?
    0.95
    ./
    0.87
    ,,
    0.86
    Activations Density 0.011%

    No Known Activations