© 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. 31632
    Prev
    Next
    INDEX
    Explanations

    numerical or statistical data points and their associated values

    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
    497
    +0.12
    0.5%
    488
    +0.10
    0.4%
    442
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    316
    +0.12
    0.15
    153
    +0.10
    0.15
    512
    +0.09
    0.13
    Negative Logits
     Heard
    -0.78
     lett
    -0.76
     Chronicle
    -0.72
     stuff
    -0.68
     Bleach
    -0.66
     Chop
    -0.66
     Choice
    -0.65
     Photographer
    -0.64
    tainment
    -0.64
    Glass
    -0.63
    POSITIVE LOGITS
     âĪ¼
    1.21
     âĪĴ
    1.19
    âĪĴ
    1.06
    ±
    1.03
    ¶
    0.97
     (âĪĴ
    0.97
    âĢIJ
    0.96
    γ
    0.94
    β
    0.91
     âī¥
    0.88
    Activations Density 0.336%

    No Known Activations