© 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. 4481
    Prev
    Next
    INDEX
    Explanations

    numerical data or values

    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
    482
    +0.13
    0.6%
    99
    +0.10
    0.5%
    273
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    239
    +0.13
    0.05
    482
    +0.10
    0.04
    153
    +0.10
    0.04
    Negative Logits
     EntityItem
    -0.68
    Ñĭ
    -0.64
    itory
    -0.62
     swearing
    -0.61
     Luther
    -0.61
     Beir
    -0.59
     Scotia
    -0.59
    arians
    -0.58
    anship
    -0.58
     Kass
    -0.57
    POSITIVE LOGITS
    teenth
    1.12
    teen
    1.11
    04
    0.85
    03
    0.82
    0000
    0.81
    07
    0.81
    34
    0.81
    Bs
    0.80
    990
    0.79
    RM
    0.78
    Activations Density 0.181%

    No Known Activations