© 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. 28966
    Prev
    Next
    INDEX
    Explanations

    references to crime and related legal matters

    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
    280
    +0.14
    0.7%
    373
    +0.11
    0.5%
    530
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    280
    +0.14
    0.07
    659
    +0.11
    0.08
    31
    +0.11
    0.07
    Negative Logits
     Dill
    -1.02
    dt
    -1.00
     Dai
    -0.98
     Teg
    -0.96
     Dart
    -0.93
     Droid
    -0.92
    DD
    -0.91
     Ding
    -0.90
     Tad
    -0.87
     TD
    -0.86
    POSITIVE LOGITS
    oul
    0.92
    ococ
    0.84
    oun
    0.83
     Loch
    0.83
    OC
    0.81
    aul
    0.81
    Roaming
    0.80
    oca
    0.77
    olar
    0.76
    ospace
    0.75
    Activations Density 4.950%

    No Known Activations