© 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. 8-RES_POST_32K-OAI
    11. 9072
    Prev
    Next
    INDEX
    Explanations

    high-frequency motifs and structures in the text

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_8.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    standard
    Context Size
    64
    Dataset
    Skylion007/openwebtext
    Activation Function
    topk
    Embeds
    IFrame
    Link
    Neuron Alignment
    Index
    Value
    % of L₁
    717
    +0.10
    0.5%
    764
    +0.10
    0.5%
    690
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    674
    +0.10
    0.05
    314
    +0.10
    -0.01
    232
    +0.09
    0.06
    Negative Logits
     Vert
    -0.78
     Percy
    -0.73
     Vald
    -0.71
    Stan
    -0.70
    stan
    -0.70
     Bulgar
    -0.68
    ãĥĺ
    -0.68
     Darkness
    -0.65
     PRES
    -0.64
     UPS
    -0.64
    POSITIVE LOGITS
    i
    1.55
    iar
    1.06
    ii
    1.06
    iak
    1.03
    xi
    1.02
    iki
    1.01
    iani
    1.01
    iy
    0.99
    iology
    0.98
    igi
    0.98
    Activations Density 1.252%

    No Known Activations