© 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. 28161
    Prev
    Next
    INDEX
    Explanations

    specific character names and their associated contexts in narratives

    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
    651
    +0.11
    0.5%
    137
    +0.11
    0.5%
    716
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.11
    0.01
    208
    +0.11
    0.01
    556
    +0.11
    0.01
    Negative Logits
    rences
    -0.79
    banks
    -0.71
    onics
    -0.69
    men
    -0.69
    bies
    -0.69
    chens
    -0.69
    onica
    -0.69
    prises
    -0.68
    lings
    -0.68
    fix
    -0.65
    POSITIVE LOGITS
    å°
    1.05
    æ³
    1.03
     ILCS
    0.97
    ç¥ŀ
    0.94
    女
    0.93
    ãĤ´ãĥ³
    0.87
    çİĭ
    0.83
    å¯
    0.82
    çļ
    0.77
    ŃĶ
    0.77
    Activations Density 0.012%

    No Known Activations