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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 20909
    Prev
    Next
    INDEX
    Explanations

    functions or methods in a programming context

    oai_token-act-pair · gpt-3.5-turbo

    function call syntax in programming code

    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
    stal
    -0.89
    warts
    -0.84
    worldly
    -0.72
    stood
    -0.71
    anda
    -0.71
    ties
    -0.68
    sem
    -0.67
    mong
    -0.67
    meat
    -0.66
    water
    -0.65
    POSITIVE LOGITS
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    1.04
     externalToEVAOnly
    0.85
     Returns
    0.80
    /-
    0.75
    #$
    0.71
    SourceFile
    0.70
     Bett
    0.69
    []
    0.69
    ãĤ´ãĥ³
    0.68
     Oops
    0.68
    Activations Density 0.017%

    No Known Activations