© 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. 30299
    Prev
    Next
    INDEX
    Explanations

    phrases denoting continuity and transitions in narrative descriptions

    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
    373
    +0.12
    0.6%
    260
    +0.12
    0.5%
    325
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    756
    +0.12
    -0.00
    437
    +0.12
    0.03
    269
    +0.10
    0.03
    Negative Logits
    luck
    -0.72
    pload
    -0.70
     [&
    -0.70
    ellen
    -0.70
    bies
    -0.69
    20439
    -0.67
    hai
    -0.67
    cham
    -0.66
    cknowled
    -0.66
    lik
    -0.64
    POSITIVE LOGITS
     culmin
    0.90
     ending
    0.85
     escal
    0.84
     culminating
    0.83
    Finish
    0.83
     progressing
    0.82
     Continued
    0.81
     progressively
    0.81
     progressed
    0.80
     ends
    0.79
    Activations Density 1.374%

    No Known Activations