© 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. 32767
    Prev
    Next
    INDEX
    Explanations

    references to historical events and their impacts

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    751
    +0.10
    0.5%
    285
    +0.10
    0.4%
    698
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    539
    +0.10
    0.14
    550
    +0.10
    0.14
    640
    +0.10
    0.13
    Negative Logits
     Protoss
    -0.65
     Leilan
    -0.61
    çīĪ
    -0.61
    ilo
    -0.60
    MN
    -0.59
    lis
    -0.57
    MX
    -0.57
    olean
    -0.56
     Mineral
    -0.56
     Mile
    -0.56
    POSITIVE LOGITS
    together
    0.89
    until
    0.84
    instead
    0.80
    along
    0.79
    cause
    0.79
    rather
    0.77
    albeit
    0.77
    without
    0.76
    yet
    0.76
    except
    0.75
    Activations Density 1.174%

    No Known Activations