© 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. 31428
    Prev
    Next
    INDEX
    Explanations

    pieces of code or programming constructs

    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
    +0.14
    0.6%
    166
    +0.09
    0.4%
    206
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.14
    0.07
    699
    +0.09
    0.03
    314
    +0.09
    -0.02
    Negative Logits
     Coinbase
    -0.81
     navig
    -0.81
     Ibn
    -0.76
     avocado
    -0.75
    aunder
    -0.74
     wearable
    -0.73
     Fleming
    -0.73
     contraceptive
    -0.72
     healthcare
    -0.72
    aunders
    -0.72
    POSITIVE LOGITS
    ------
    1.99
    -------
    1.94
    --------
    1.91
    ----
    1.87
    -----------
    1.85
    ------------
    1.83
    ----------
    1.81
    --------------
    1.74
    -----
    1.72
    ---------
    1.69
    Activations Density 0.627%

    No Known Activations