© 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. 26542
    Prev
    Next
    INDEX
    Explanations

    specific numerical or date references related to government discussions and actions

    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%
    719
    +0.09
    0.4%
    260
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    123
    +0.13
    0.05
    220
    +0.09
    0.04
    667
    +0.09
    0.03
    Negative Logits
     ];
    -0.78
    vati
    -0.70
     Babel
    -0.70
    plin
    -0.67
     Leilan
    -0.63
    "],
    -0.63
    onement
    -0.63
     Trayvon
    -0.63
     ].
    -0.62
    "]
    -0.61
    POSITIVE LOGITS
    %)
    0.79
     votes
    0.75
     episodes
    0.69
    CW
    0.66
    KB
    0.64
    MB
    0.64
    kB
    0.64
     bites
    0.64
    ãĤ¦ãĤ¹
    0.63
    +)
    0.63
    Activations Density 0.241%

    No Known Activations