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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Residual Post - 32k
    5. 10-RES_POST_32K-OAI
    6. 28142
    Prev
    Next
    INDEX
    Explanations

    references to individuals and their roles or relationships in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_10.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    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
    731
    +0.12
    0.6%
    718
    +0.11
    0.5%
    276
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    762
    +0.12
    0.07
    15
    +0.11
    0.05
    718
    +0.11
    0.05
    Negative Logits
    76561
    -0.82
    quickShipAvailable
    -0.74
     Needs
    -0.74
    needs
    -0.73
    MpServer
    -0.69
    soDeliveryDate
    -0.66
    GGGGGGGG
    -0.66
    Appearances
    -0.65
    ANC
    -0.64
     Continued
    -0.64
    POSITIVE LOGITS
     engage
    1.43
     introduce
    1.43
     wrestle
    1.43
     participate
    1.42
     perform
    1.41
     declare
    1.38
     lose
    1.36
     behave
    1.36
     deliver
    1.35
     undertake
    1.35
    Activations Density 0.378%

    No Known Activations