© 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. 5896
    Prev
    Next
    INDEX
    Explanations

    specific numerical references and citations within academic or critical texts

    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
    488
    +0.13
    0.6%
    547
    +0.10
    0.4%
    18
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    488
    +0.13
    0.05
    719
    +0.10
    0.04
    326
    +0.09
    0.04
    Negative Logits
     Tide
    -0.60
    Mail
    -0.58
    ordinate
    -0.58
     disposable
    -0.56
    emade
    -0.56
     adulthood
    -0.56
     Hawaiian
    -0.56
    oat
    -0.55
    venge
    -0.55
     treadmill
    -0.55
    POSITIVE LOGITS
     ff
    1.22
     seq
    1.10
     sq
    1.00
    ff
    0.96
     âĨij
    0.95
    .;
    0.88
     NRS
    0.83
     pg
    0.79
     onwards
    0.77
    fn
    0.77
    Activations Density 0.209%

    No Known Activations