© 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. 3-RES-JB
    11. 6112
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Kol" and variations of it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    names related to different individuals or entities, such as "Kopitar" and "Kolomoisky"

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CLASSIFIED
    -0.79
    gered
    -0.69
    Western
    -0.66
    ÃįÃį
    -0.64
    icist
    -0.63
    LEASE
    -0.63
     heads
    -0.62
     nerves
    -0.61
    IBLE
    -0.61
    Ign
    -0.61
    POSITIVE LOGITS
     Kop
    1.08
    itsch
    0.99
    anski
    0.93
    won
    0.92
     Klux
    0.85
    oslov
    0.84
    inski
    0.82
    owski
    0.82
    pps
    0.82
    sten
    0.79
    Activations Density 0.006%

    No Known Activations