© 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. 8-RES-JB
    11. 2399
    Prev
    Next
    INDEX
    Explanations

    names or mentions related to "Kol" with varying degrees of detail

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Kol."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MG
    -0.73
    ISTER
    -0.70
    ONDON
    -0.65
    IST
    -0.65
    ãĥ³ãĤ¸
    -0.64
    ALLY
    -0.64
     Extreme
    -0.63
    achusetts
    -0.63
    aneously
    -0.63
    ãĥ´ãĤ¡
    -0.63
    POSITIVE LOGITS
    oro
    0.86
    keye
    0.85
    onial
    0.85
    bin
    0.85
    ral
    0.81
    odi
    0.81
    odes
    0.80
    ody
    0.80
    rahim
    0.78
    ode
    0.76
    Activations Density 0.069%

    No Known Activations