© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 32655
    Prev
    Next
    INDEX
    Explanations

    instances of the character 'ľ'

    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
    356
    +0.09
    0.4%
    52
    +0.09
    0.4%
    16
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    650
    +0.09
    0.11
    314
    +0.09
    0.02
    675
    +0.09
    0.09
    Negative Logits
    dos
    -0.84
     clipboard
    -0.70
    auga
    -0.69
     apes
    -0.69
    ngth
    -0.69
    rats
    -0.68
     princ
    -0.67
    mble
    -0.66
    raints
    -0.66
     terminals
    -0.65
    POSITIVE LOGITS
    âĶĢâĶĢ
    1.05
    isher
    0.98
    é£
    0.96
    ãĥĩãĤ£
    0.95
    asted
    0.92
    ishers
    0.91
    ICE
    0.88
    ishing
    0.88
    asts
    0.88
    ãĥ¼ãĥ«
    0.87
    Activations Density 0.348%

    No Known Activations