© 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. 26851
    Prev
    Next
    INDEX
    Explanations

    special characters, numbers, or elements typically found in coding or programming 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
    373
    +0.13
    0.6%
    442
    +0.12
    0.5%
    455
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.13
    -0.01
    138
    +0.12
    0.03
    447
    +0.11
    0.03
    Negative Logits
     nodd
    -0.78
     SOS
    -0.66
     Orn
    -0.65
     640
    -0.64
     Aware
    -0.63
     looph
    -0.62
     contr
    -0.62
     Painter
    -0.62
     Able
    -0.61
     Sauce
    -0.61
    POSITIVE LOGITS
    04
    1.31
    06
    1.29
    03
    1.28
    05
    1.27
    07
    1.25
    08
    1.25
    02
    1.25
    01
    1.24
    00
    1.13
    09
    1.12
    Activations Density 0.735%

    No Known Activations