© 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. 31158
    Prev
    Next
    INDEX
    Explanations

    actions related to physical movements and demonstrations

    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
    374
    +0.13
    0.6%
    47
    +0.10
    0.5%
    572
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    59
    +0.13
    0.06
    730
    +0.10
    0.08
    47
    +0.10
    0.07
    Negative Logits
    terness
    -0.76
    âĹ¼
    -0.73
    Depth
    -0.68
    amina
    -0.67
    sense
    -0.67
    Strength
    -0.67
    zinski
    -0.67
    Phys
    -0.66
    xual
    -0.66
    ysical
    -0.66
    POSITIVE LOGITS
     banners
    1.38
     balloons
    1.24
     posters
    1.23
     benches
    1.21
     chairs
    1.20
     blankets
    1.19
     tents
    1.19
     poles
    1.18
     cardboard
    1.17
     candles
    1.15
    Activations Density 1.439%

    No Known Activations