© 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. 26203
    Prev
    Next
    INDEX
    Explanations

    the repeated phrase "going" in various contexts

    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
    363
    +0.12
    0.5%
    2
    +0.11
    0.5%
    566
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    566
    +0.12
    0.06
    701
    +0.11
    0.05
    200
    +0.10
    0.06
    Negative Logits
    alys
    -0.87
    umerable
    -0.82
    ufficient
    -0.81
    iew
    -0.80
    acceptable
    -0.77
    538
    -0.73
    ursor
    -0.71
    ascript
    -0.69
    rils
    -0.69
    earcher
    -0.65
    POSITIVE LOGITS
     home
    0.80
     HOME
    0.80
     mad
    0.78
    nin
    0.74
     crazy
    0.68
     HAM
    0.67
    home
    0.64
     late
    0.64
     psycho
    0.63
     paranoid
    0.63
    Activations Density 0.192%

    No Known Activations