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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 20034
    Prev
    Next
    INDEX
    Explanations

    specific names containing the substring 'Kn'

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of the name "Kn."

    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
    quickShipAvailable
    -0.77
    DEM
    -0.70
     Bahrain
    -0.68
    sem
    -0.67
    REDACTED
    -0.66
    IUM
    -0.64
     Venezuelan
    -0.63
     Sunni
    -0.63
     Lima
    -0.63
    ahime
    -0.62
    POSITIVE LOGITS
     Kn
    1.20
    ivable
    1.03
    uckle
    0.99
    Kn
    0.98
    kn
    0.92
    ocking
    0.92
    uckles
    0.90
    ows
    0.89
    uth
    0.87
    reditary
    0.83
    Activations Density 0.007%

    No Known Activations