© 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
    3. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    5. GPT2-Small
    7. Residual Post - 32k
    9. 10-RES_POST_32K-OAI
    11. 32466
    Prev
    Next
    INDEX
    Explanations

    numeric representations of measurements, especially related to calibers and millimeter specifications

    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
    0
    +0.11
    0.5%
    63
    +0.11
    0.5%
    289
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    589
    +0.11
    0.02
    678
    +0.11
    0.02
    289
    +0.10
    0.01
    Negative Logits
    lez
    -0.96
    leased
    -0.78
    eer
    -0.76
    actionDate
    -0.74
    comes
    -0.68
    hurst
    -0.67
    ebted
    -0.67
    ciating
    -0.66
    rador
    -0.66
    alia
    -0.66
    POSITIVE LOGITS
     thick
    0.90
     diameter
    0.86
     thickness
    0.74
    mmm
    0.74
     radiator
    0.72
     holes
    0.71
     Negative
    0.71
    ²
    0.71
     socket
    0.69
     equivalent
    0.68
    Activations Density 0.085%

    No Known Activations