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. 24007
    Prev
    Next
    INDEX
    Explanations

    words related to names, especially those containing the letter sequence "omp"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the syllable "omp" and "ump" 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
     angels
    -0.62
     CPC
    -0.60
     mole
    -0.60
    âĶĢâĶĢ
    -0.59
    VERTISEMENT
    -0.57
     Wanted
    -0.56
     mainline
    -0.56
     Engineers
    -0.55
     Cath
    -0.55
     Curiosity
    -0.54
    POSITIVE LOGITS
    fen
    1.00
    inski
    0.98
    olit
    0.98
    olitan
    0.97
    oleon
    0.97
    onent
    0.96
    osit
    0.95
    ohl
    0.92
    apa
    0.91
    eli
    0.91
    Activations Density 0.083%

    No Known Activations