© 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. 26217
    Prev
    Next
    INDEX
    Explanations

    phrases indicating varying degrees of magnitude or importance

    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
    373
    +0.13
    0.6%
    175
    +0.12
    0.6%
    113
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    175
    +0.13
    0.02
    95
    +0.12
    0.03
    425
    +0.12
    0.02
    Negative Logits
    oppers
    -0.75
    etsk
    -0.69
    qqa
    -0.64
    querque
    -0.63
     bandwagon
    -0.60
     rolls
    -0.60
    protect
    -0.59
    phrine
    -0.59
    ãĥ¯ãĥ³
    -0.58
     bluff
    -0.57
    POSITIVE LOGITS
     extent
    1.33
     degree
    1.27
     lesser
    0.96
     varying
    0.84
     considerable
    0.84
     Degree
    0.81
    degree
    0.80
     ext
    0.77
     greater
    0.77
     fault
    0.76
    Activations Density 0.409%

    No Known Activations