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

    Neuronpedia

    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. 29281
    Prev
    Next
    INDEX
    Explanations

    specific keywords and variables often related to programming or technical content

    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
    416
    +0.10
    0.5%
    526
    +0.10
    0.4%
    745
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    66
    +0.10
    0.02
    586
    +0.10
    0.01
    526
    +0.09
    -0.01
    Negative Logits
     CTR
    -0.62
    ainers
    -0.62
    IDS
    -0.59
    ifter
    -0.59
    GBT
    -0.58
     Parenthood
    -0.58
    rity
    -0.57
    guyen
    -0.56
    ierre
    -0.56
    nces
    -0.56
    POSITIVE LOGITS
    ahime
    0.91
    \-
    0.88
    )|
    0.77
    éŃĶ
    0.69
    lon
    0.64
    igan
    0.62
    star
    0.60
    tera
    0.60
    letico
    0.60
    ãĥĥãĥī
    0.59
    Activations Density 0.152%

    No Known Activations