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. 4-RES-JB
    6. 3382
    Prev
    Next
    INDEX
    Explanations

    words related to famous personalities or significant figures

    oai_token-act-pair · gpt-3.5-turbo

    the repeated instance of the letters "ll."

    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
     guiActiveUn
    -0.79
    EStream
    -0.76
    */(
    -0.75
    ¥ŀ
    -0.75
    uliffe
    -0.69
    lished
    -0.68
    joined
    -0.65
     exha
    -0.63
    ãĥ¯ãĥ³
    -0.62
     frustrated
    -0.62
    POSITIVE LOGITS
    oyd
    1.32
    uminati
    1.15
    ounge
    1.10
    inois
    1.03
    ows
    1.01
    ibrary
    0.98
    iard
    0.97
    ength
    0.96
    umi
    0.96
    uci
    0.95
    Activations Density 0.024%

    No Known Activations