© 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. 31347
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "strike" and its variations, indicating a focus on actions or incidents involving impact or confrontation

    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
    366
    +0.12
    0.5%
    630
    +0.10
    0.4%
    276
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    750
    +0.12
    0.05
    566
    +0.10
    0.04
    696
    +0.09
    0.04
    Negative Logits
    adelphia
    -0.75
    Winged
    -0.66
    stery
    -0.62
    uploads
    -0.60
     Leilan
    -0.60
    href
    -0.60
     [+
    -0.59
     Kardash
    -0.59
    til
    -0.58
    ples
    -0.58
    POSITIVE LOGITS
     fear
    0.98
     gold
    0.85
     terror
    0.84
     chord
    0.83
     deals
    0.77
     pose
    0.73
     resemblance
    0.70
     blows
    0.70
     bargain
    0.69
     stride
    0.69
    Activations Density 0.951%

    No Known Activations