© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 7274
    Prev
    Next
    INDEX
    Explanations

    variations of the suffix "-uth" and "-air" in words

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    215
    +0.11
    0.5%
    20
    +0.11
    0.5%
    671
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.11
    -0.01
    118
    +0.11
    0.03
    487
    +0.10
    0.03
    Negative Logits
    schild
    -0.66
    hemy
    -0.62
    nen
    -0.61
     Hath
    -0.58
    antha
    -0.57
     Juno
    -0.57
     diseng
    -0.54
     STATS
    -0.54
     Split
    -0.54
     Tsarnaev
    -0.53
    POSITIVE LOGITS
    pillar
    0.98
    emporary
    0.81
    ulative
    0.79
    pill
    0.79
    aminer
    0.77
    etary
    0.73
    ulhu
    0.71
    ellation
    0.70
    grave
    0.70
    abis
    0.69
    Activations Density 0.207%

    No Known Activations