© 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 EvalsExportsAPI 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. 30735
    Prev
    Next
    INDEX
    Explanations

    numerical data and mathematical expressions

    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
    118
    +0.15
    0.7%
    326
    +0.13
    0.6%
    6
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    316
    +0.15
    0.08
    326
    +0.13
    0.08
    96
    +0.13
    0.06
    Negative Logits
     disapp
    -0.80
     streng
    -0.77
     advoc
    -0.76
     nodd
    -0.76
    etsk
    -0.71
     quir
    -0.70
     sensing
    -0.70
    amaz
    -0.69
     antioxid
    -0.69
     suscept
    -0.68
    POSITIVE LOGITS
    000000
    1.40
    0000
    1.39
    00000
    1.39
    9999
    1.38
    200000
    1.34
    999
    1.31
    000
    1.30
    500
    1.28
    0000000
    1.25
    200
    1.22
    Activations Density 0.527%

    No Known Activations