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. 3-RES-JB
    6. 19845
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Ole"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Ole Miss" in the text

    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
    ãĤ½
    -0.84
    ãĤ¢ãĥ«
    -0.81
    è¦ļéĨĴ
    -0.75
    stroke
    -0.74
    ãĥ¥
    -0.72
     IST
    -0.71
    ULT
    -0.70
    ãĥŁ
    -0.67
    ãĥĩ
    -0.66
    Material
    -0.66
    POSITIVE LOGITS
     Ole
    0.95
    oshenko
    0.90
    phan
    0.86
    enko
    0.83
    estone
    0.83
    quin
    0.83
    terness
    0.82
    akia
    0.82
    yss
    0.81
    etsk
    0.80
    Activations Density 0.007%

    No Known Activations