© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 11-RES-JB
    11. 21960
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to a specific entity or person named "Kan."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Kan" and variations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Imm
    -0.65
     favour
    -0.62
     luck
    -0.60
     Carbuncle
    -0.59
     Integrity
    -0.59
     charism
    -0.58
     encour
    -0.58
     Aires
    -0.55
     hope
    -0.55
    aturday
    -0.54
    POSITIVE LOGITS
    hai
    1.12
    ataka
    1.07
    eki
    1.02
    erva
    1.02
    asaki
    0.99
    thal
    0.99
    ji
    0.99
    amaru
    0.96
    pai
    0.95
    ako
    0.93
    Activations Density 0.052%

    No Known Activations