© 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. 22799
    Prev
    Next
    INDEX
    Explanations

    phrases relating to the name "Krzanich"

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of the name "Krzanich."

    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
    Journal
    -0.71
    âĸ¬âĸ¬
    -0.69
    eering
    -0.69
    journal
    -0.68
    hibition
    -0.68
    */(
    -0.65
    communication
    -0.64
     quo
    -0.64
    recomm
    -0.63
    payer
    -0.63
    POSITIVE LOGITS
     Kr
    1.16
    usk
    1.08
    istani
    1.08
    ©¶æ¥µ
    1.00
    assic
    0.99
    asus
    0.95
    ataka
    0.93
    mares
    0.89
    ota
    0.88
    atell
    0.85
    Activations Density 0.004%

    No Known Activations