© 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. 4-RES-JB
    11. 7802
    Prev
    Next
    INDEX
    Explanations

    names containing the syllable "ko"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the token "ko" in various contexts

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

    No Comments

    Negative Logits
     glim
    -0.77
    Ö¼
    -0.75
    glass
    -0.74
     narrator
    -0.73
    IDENT
    -0.73
    Subject
    -0.72
    icist
    -0.71
    ologies
    -0.70
     behavi
    -0.69
    shire
    -0.69
    POSITIVE LOGITS
    zzi
    1.28
    ppa
    1.08
    zzo
    1.03
    ichi
    0.97
    pps
    0.95
    pper
    0.93
    ven
    0.93
    ombat
    0.90
    wu
    0.90
    opa
    0.90
    Activations Density 0.010%

    No Known Activations