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. 2358
    Prev
    Next
    INDEX
    Explanations

    keywords related to programming and coding

    oai_token-act-pair · gpt-3.5-turbo

    programming-related actions and functions, particularly those involving data manipulation and updates

    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
    guyen
    -0.86
    laus
    -0.82
    allery
    -0.80
     Frie
    -0.79
    antz
    -0.79
    oths
    -0.78
    itton
    -0.78
    atti
    -0.77
    isine
    -0.72
    arag
    -0.72
    POSITIVE LOGITS
    able
    1.07
    ABLE
    0.91
    ables
    0.86
    ments
    0.79
    ãĥ¼ãĤ¯
    0.79
     button
    0.78
    ()
    0.77
    Flags
    0.76
    ings
    0.76
    ability
    0.74
    Activations Density 0.146%

    No Known Activations