© 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. 0-RES-JB
    11. 20511
    Prev
    Next
    INDEX
    Explanations

    mentions or references to the name "Kek"

    oai_token-act-pair · gpt-3.5-turbo

    the letter 'k' and its variations in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     proceedings
    -0.66
     saline
    -0.60
     contraception
    -0.58
     circumstance
    -0.57
    istical
    -0.57
     deficit
    -0.55
     facilit
    -0.55
     rehe
    -0.55
    RANT
    -0.54
     Recre
    -0.54
    POSITIVE LOGITS
    k
    3.77
    kr
    2.22
    kl
    2.11
    K
    2.05
    kk
    2.04
    kt
    1.98
    ks
    1.93
    kh
    1.87
    kas
    1.84
    kish
    1.84
    Activations Density 0.027%

    No Known Activations