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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 5-RES-JB
    6. 16285
    Prev
    Next
    INDEX
    Explanations

    the string "bur" with different suffixes and various contexts

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the substring "bur" in various contexts

    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
    assian
    -0.74
    ermott
    -0.66
    inen
    -0.65
     Ragnarok
    -0.62
     Borg
    -0.61
     Hat
    -0.61
    arin
    -0.61
    arrell
    -0.61
     Biological
    -0.60
    enced
    -0.60
    POSITIVE LOGITS
    ket
    0.89
    ãĥĦ
    0.85
    acters
    0.84
    ker
    0.84
    pload
    0.81
    kers
    0.81
    ernels
    0.80
    ging
    0.78
    ple
    0.78
    ãĤ¡
    0.78
    Activations Density 0.045%

    No Known Activations