© 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. 28325
    Prev
    Next
    INDEX
    Explanations

    alternate phrases or conjunctions indicating choices or options

    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
    276
    +0.11
    0.5%
    485
    +0.10
    0.5%
    418
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    333
    +0.11
    0.03
    485
    +0.10
    0.03
    545
    +0.10
    0.02
    Negative Logits
     666
    -0.76
     777
    -0.76
     701
    -0.75
     1886
    -0.71
     808
    -0.70
    NESS
    -0.68
     392
    -0.66
    UTC
    -0.66
     625
    -0.65
     299
    -0.64
    POSITIVE LOGITS
    fif
    1.00
    three
    0.91
    four
    0.89
    ties
    0.82
    irds
    0.78
    thirds
    0.78
    ten
    0.77
    angled
    0.76
    five
    0.76
     four
    0.75
    Activations Density 0.217%

    No Known Activations