© 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. 32101
    Prev
    Next
    INDEX
    Explanations

    references to the word "was."

    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
    454
    +0.09
    0.4%
    367
    +0.09
    0.4%
    127
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    55
    +0.09
    0.11
    7
    +0.09
    0.09
    102
    +0.09
    0.09
    Negative Logits
    negative
    -0.64
     dodging
    -0.62
    talking
    -0.60
     sqor
    -0.58
     Reporter
    -0.58
    umbing
    -0.57
     caveats
    -0.56
    egg
    -0.55
    Dialogue
    -0.55
    esthes
    -0.55
    POSITIVE LOGITS
     created
    1.25
     founded
    1.24
     invented
    1.22
     pioneered
    1.21
     coined
    1.20
     launched
    1.13
     devised
    1.12
     developed
    1.11
     first
    1.04
     formed
    1.04
    Activations Density 0.554%

    No Known Activations