© 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. 10-RES-JB
    11. 10696
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to the state of Oklahoma

    oai_token-act-pair · gpt-3.5-turbo

    the occurrence of the term "Ok" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     spoiled
    -0.76
     lav
    -0.67
     free
    -0.65
     istg
    -0.63
    âĢ¢âĢ¢âĢ¢âĢ¢
    -0.60
     Horowitz
    -0.60
     starved
    -0.60
     Gems
    -0.59
     thwarted
    -0.59
     simul
    -0.58
    POSITIVE LOGITS
    lahoma
    1.60
    onom
    1.14
    awaru
    1.13
    lah
    1.12
    unin
    1.01
    la
    0.96
    azaki
    0.93
    obo
    0.90
    anda
    0.88
    alo
    0.86
    Activations Density 0.024%

    No Known Activations