© 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. 10-RES_POST_32K-OAI
    11. 31471
    Prev
    Next
    INDEX
    Explanations

    expressions related to frequency and incidence over time

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

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    558
    +0.11
    0.5%
    477
    +0.10
    0.4%
    218
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    162
    +0.11
    0.04
    269
    +0.10
    0.04
    477
    +0.10
    0.03
    Negative Logits
    eki
    -0.64
    izo
    -0.57
    ilitarian
    -0.56
     Clown
    -0.55
     Zombies
    -0.55
    ModLoader
    -0.55
     benches
    -0.54
     ceilings
    -0.54
    UFF
    -0.53
    ypes
    -0.53
    POSITIVE LOGITS
     year
    1.60
    year
    1.32
     month
    1.29
     YEAR
    1.19
    month
    1.09
     decade
    1.09
     day
    1.06
     ann
    1.06
     Year
    1.05
     week
    1.05
    Activations Density 0.244%

    No Known Activations