© 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. 0-RES-JB
    11. 15564
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Kub" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    names related to individuals and specific brands or products

    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
     Hess
    -0.77
    Madison
    -0.75
     DOE
    -0.71
     GS
    -0.70
     NJ
    -0.70
    resist
    -0.70
     TT
    -0.69
     CPS
    -0.69
    NJ
    -0.69
    annie
    -0.69
    POSITIVE LOGITS
     Kub
    3.15
    Ub
    2.41
     Ub
    2.02
     ub
    1.70
     Kab
    1.45
     Caldwell
    1.41
     Lob
    1.38
     Coc
    1.32
     Tomb
    1.27
     Gob
    1.17
    Activations Density 0.017%

    No Known Activations