© 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. 1-RES-JB
    11. 3749
    Prev
    Next
    INDEX
    Explanations

    names of people or places starting with "Kon"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals, particularly those named "Kon" and "Klopp"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UCT
    -0.76
     Carrie
    -0.75
    hips
    -0.69
    ħĭ
    -0.68
    ounty
    -0.67
    Ö¼
    -0.66
    Constructed
    -0.64
     Immunity
    -0.64
     Episcopal
    -0.64
    Journal
    -0.64
    POSITIVE LOGITS
    jac
    1.14
    stant
    1.13
     Kon
    1.08
    oha
    1.04
    osuke
    1.00
    nen
    0.97
    heim
    0.90
    nect
    0.89
    kus
    0.89
    omy
    0.89
    Activations Density 0.004%

    No Known Activations