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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 16039
    Prev
    Next
    INDEX
    Explanations

    names or titles with the suffix "Sr."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals or titles, particularly with the prefix "Sr."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enaries
    -0.80
    insula
    -0.71
    iage
    -0.69
    sylvania
    -0.68
     Dickinson
    -0.65
    ision
    -0.64
     inhib
    -0.63
    umenthal
    -0.63
    govtrack
    -0.61
    ãĥī
    -0.60
    POSITIVE LOGITS
    pered
    0.90
    é¾įåĸļ士
    0.81
     Chak
    0.81
    tis
    0.81
    pering
    0.77
    inka
    0.77
    nor
    0.76
    Lua
    0.76
    uve
    0.73
    Py
    0.72
    Activations Density 0.030%

    No Known Activations