© 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. 3-RES-JB
    11. 2839
    Prev
    Next
    INDEX
    Explanations

    references to locations or entities containing the substring "Ok"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Ok"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     lav
    -0.85
    éĹ
    -0.76
    âĢ¢âĢ¢âĢ¢âĢ¢
    -0.72
    schild
    -0.70
    TPPStreamerBot
    -0.68
    FACE
    -0.65
    minecraft
    -0.64
     Scourge
    -0.63
    uded
    -0.63
    ãĤ¼ãĤ¦ãĤ¹
    -0.61
    POSITIVE LOGITS
    lahoma
    1.37
    ok
    0.95
     Ok
    0.86
    oks
    0.83
    unin
    0.83
    oms
    0.81
    awaru
    0.80
    lander
    0.80
    la
    0.80
    oka
    0.79
    Activations Density 0.005%

    No Known Activations