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. 7-RES-JB
    6. 6637
    Prev
    Next
    INDEX
    Explanations

    timestamps or specific points in time

    oai_token-act-pair · gpt-3.5-turbo

    phrases that contain the word "when" indicating temporal contexts or moments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hesive
    -0.70
    urally
    -0.68
    ply
    -0.68
    rolet
    -0.67
     Piece
    -0.66
    andal
    -0.63
    backer
    -0.62
    agin
    -0.62
    gan
    -0.60
    guide
    -0.59
    POSITIVE LOGITS
    abouts
    1.01
    soever
    1.01
    ornia
    0.83
     temperatures
    0.73
    wcs
    0.70
     they
    0.68
     tensions
    0.67
     we
    0.65
     millions
    0.64
     inexperienced
    0.63
    Activations Density 0.065%

    No Known Activations