Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 24524
    Prev
    Next
    INDEX
    Explanations

    names containing the letters "lee"

    oai_token-act-pair · gpt-3.5-turbo

    the name "Lee" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    itu
    -0.65
    */(
    -0.65
     hindsight
    -0.65
     CPC
    -0.62
    icates
    -0.62
    meaning
    -0.61
     Seym
    -0.61
    icate
    -0.60
    ãĥķãĤ©
    -0.58
    icating
    -0.58
    POSITIVE LOGITS
    lee
    1.33
    lees
    0.93
    pless
    0.87
    scill
    0.80
    pee
    0.79
    ce
    0.77
     ILCS
    0.76
    ves
    0.74
    ucha
    0.74
    vable
    0.74
    Activations Density 0.009%

    No Known Activations