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. 6686
    Prev
    Next
    INDEX
    Explanations

    dates in the format "month/day/year"

    oai_token-act-pair · gpt-3.5-turbo

    date and time references, along with numeric identifiers

    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
    ciating
    -0.76
    ©¶æ
    -0.75
    uese
    -0.71
    otto
    -0.71
    \/\/
    -0.69
    hiba
    -0.69
    ngth
    -0.68
    ãĤ©
    -0.68
    oshenko
    -0.68
    ãĤ£
    -0.67
    POSITIVE LOGITS
    enegger
    0.91
    bush
    0.75
     Wonderland
    0.73
    ktop
    0.65
     cents
    0.63
     Views
    0.62
    displayText
    0.62
     Vers
    0.58
    PsyNetMessage
    0.58
    fleet
    0.58
    Activations Density 0.164%

    No Known Activations