© 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. 4-RES-JB
    11. 20046
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "oke" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the character "Moke."

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

    No Comments

    Negative Logits
    ittance
    -0.63
    atile
    -0.62
    ENDED
    -0.61
    atility
    -0.60
     Adin
    -0.59
     Lub
    -0.59
     commod
    -0.59
    ENCY
    -0.58
    ugal
    -0.58
     ACTIONS
    -0.58
    POSITIVE LOGITS
    otle
    0.96
    tto
    0.90
    ls
    0.86
    oke
    0.86
    oking
    0.82
    lift
    0.81
    aways
    0.79
    eper
    0.79
    lear
    0.77
    heads
    0.76
    Activations Density 0.009%

    No Known Activations