© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Residual Post - 32k
    5. 8-RES_POST_32K-OAI
    6. 4452
    Prev
    Next
    INDEX
    Explanations

    negations or phrases indicating exceptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_8.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    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
    450
    +0.10
    0.5%
    241
    +0.10
    0.4%
    347
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    287
    +0.10
    0.07
    8
    +0.10
    0.07
    300
    +0.10
    0.08
    Negative Logits
     guiActiveUnfocused
    -0.72
    è¦ļéĨĴ
    -0.67
    versions
    -0.67
    arthed
    -0.67
    ËĪ
    -0.67
    senal
    -0.64
    cients
    -0.62
    arthy
    -0.58
    interstitial
    -0.58
    ],"
    -0.57
    POSITIVE LOGITS
    adays
    0.77
     kidding
    0.77
    cknowled
    0.77
    cknow
    0.76
    eday
    0.76
    oret
    0.73
     furthermore
    0.72
     drawback
    0.70
     moreover
    0.69
    quartered
    0.68
    Activations Density 0.840%

    No Known Activations