Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 13634
    Prev
    Next
    INDEX
    Explanations

    JavaScript variable declarations

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "var" and its variations potentially related to programming or variable declarations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     VIDEOS
    -0.79
    stem
    -0.70
    hare
    -0.66
    posts
    -0.66
    Magikarp
    -0.66
    creen
    -0.63
     prest
    -0.62
     Fundamental
    -0.61
    AX
    -0.61
    -+
    -0.61
    POSITIVE LOGITS
    ietal
    1.10
    icum
    1.06
    isher
    1.04
    icut
    0.99
    ned
    0.94
    iety
    0.94
    ishment
    0.92
    ieties
    0.92
    ica
    0.90
    ning
    0.89
    Activations Density 0.019%

    No Known Activations