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. 691
    Prev
    Next
    INDEX
    Explanations

    dates and times in a format like "MM/DD/YYYY, HH:MM AM/PM" or "HH:MM"

    oai_token-act-pair · gpt-3.5-turbo

    references to popular events or notable occurrences

    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
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.49
     tires
    -0.47
     hom
    -0.45
     domest
    -0.45
     artificial
    -0.43
    blance
    -0.42
     cultivation
    -0.41
     tire
    -0.41
     bot
    -0.41
    omorphic
    -0.41
    POSITIVE LOGITS
    Dialogue
    0.54
     Advice
    0.52
    Winged
    0.51
    ixie
    0.48
     opacity
    0.47
    Ñĭ
    0.46
    rench
    0.46
    gans
    0.46
    Quotes
    0.46
    pite
    0.45
    Activations Density 0.481%

    No Known Activations