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. 6-RES-JB
    6. 10358
    Prev
    Next
    INDEX
    Explanations

    dates, particularly in the format of months and years

    oai_token-act-pair · gpt-3.5-turbo

    dates and numerical sequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enhagen
    -0.79
    ogle
    -0.71
    elsen
    -0.70
    psey
    -0.66
     scrolls
    -0.63
    anamo
    -0.60
     selfies
    -0.57
    lees
    -0.56
     microphones
    -0.56
    ãĤ½
    -0.55
    POSITIVE LOGITS
    Ö¼
    0.76
     guiActiveUnfocused
    0.65
     Caucasus
    0.61
    ĨĴ
    0.61
    CEPT
    0.59
    Controller
    0.59
    elsius
    0.57
     irreversible
    0.57
    omaly
    0.57
    SPONSORED
    0.57
    Activations Density 1.056%

    No Known Activations