© 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. 2-RES-JB
    11. 978
    Prev
    Next
    INDEX
    Explanations

    the syllable "Kab"

    oai_token-act-pair · gpt-4-turbo

    phrases related to a specific name or topic (Kab)

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Kab," indicating a focus on a specific character or subject related to that name

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vironment
    -0.90
    psons
    -0.90
    ittee
    -0.77
    Ö¼
    -0.77
    ancial
    -0.76
    perature
    -0.75
    itance
    -0.73
    icist
    -0.72
    âĸij
    -0.72
     Yankee
    -0.71
    POSITIVE LOGITS
    quet
    0.93
    yrinth
    0.86
     Kab
    0.86
    quer
    0.77
    hov
    0.75
    duct
    0.74
    wana
    0.71
    uchi
    0.70
     Ezek
    0.70
    ha
    0.69
    Activations Density 0.016%

    No Known Activations