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. 0-RES-JB
    6. 10695
    Prev
    Next
    INDEX
    Explanations

    specific locations or names containing the string "kh" or "ikh"

    oai_token-act-pair · gpt-3.5-turbo

    references to specific locations, particularly related to "Khan Sheikhoun."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     print
    -0.73
     cider
    -0.68
     meta
    -0.62
     immune
    -0.61
     prints
    -0.61
     reinforcements
    -0.61
     Barney
    -0.60
     canned
    -0.59
     Terminal
    -0.59
     past
    -0.58
    POSITIVE LOGITS
    kh
    4.48
    ikh
    1.72
    Kh
    1.61
     kh
    1.51
    ku
    1.46
     KH
    1.39
    kov
    1.36
    akh
    1.36
    kar
    1.33
    hz
    1.32
    Activations Density 0.018%

    No Known Activations