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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Residual Post - 32k
    5. 6-RES_POST_32K-OAI
    6. 4224
    Prev
    Next
    INDEX
    Explanations

    numerical data and percentages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_6.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    standard
    Context Size
    64
    Dataset
    Skylion007/openwebtext
    Activation Function
    topk
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    401
    +0.11
    0.5%
    230
    +0.10
    0.4%
    206
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    472
    +0.11
    0.05
    316
    +0.10
    0.06
    462
    +0.10
    0.05
    Negative Logits
    undo
    -0.75
    matic
    -0.71
    itiveness
    -0.70
    imum
    -0.69
     »
    -0.66
    Results
    -0.63
    emonium
    -0.61
    cli
    -0.61
    versions
    -0.60
    awan
    -0.60
    POSITIVE LOGITS
     MP
    0.73
    TPS
    0.66
     RF
    0.64
    íķ
    0.62
     kHz
    0.62
     MPH
    0.62
    MP
    0.60
    rake
    0.60
     sexes
    0.60
     GP
    0.59
    Activations Density 0.217%

    No Known Activations