© 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. 11-RES-JB
    11. 23948
    Prev
    Next
    INDEX
    Explanations

    the word "Ok" or variations with varying levels of activation

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Ok"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     spoiled
    -0.71
    âĸł
    -0.64
     \(\
    -0.63
     istg
    -0.63
    '>
    -0.61
    eline
    -0.60
     starved
    -0.60
     Gems
    -0.58
     Juda
    -0.57
     lav
    -0.57
    POSITIVE LOGITS
    lahoma
    1.56
    awaru
    1.23
    lah
    1.19
    onom
    1.14
    AY
    1.03
    azaki
    1.02
    LA
    0.90
    la
    0.88
    amoto
    0.84
    unin
    0.84
    Activations Density 0.034%

    No Known Activations