© 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. 28053
    Prev
    Next
    INDEX
    Explanations

    instances of comparison and differing opinions related to various subjects

    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
    459
    +0.11
    0.5%
    49
    +0.09
    0.4%
    357
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    300
    +0.11
    0.05
    49
    +0.09
    0.05
    459
    +0.09
    0.02
    Negative Logits
    "},"
    -0.72
    )|
    -0.69
     ILCS
    -0.64
    /
    -0.63
    Definition
    -0.63
    Rated
    -0.63
    lihood
    -0.63
    ISON
    -0.62
     Annotations
    -0.62
    United
    -0.62
    POSITIVE LOGITS
     merely
    1.03
     simply
    1.02
     just
    0.85
     outright
    0.79
     purely
    0.71
     solely
    0.70
     downright
    0.70
     succumb
    0.68
     prefer
    0.66
    illance
    0.65
    Activations Density 0.694%

    No Known Activations