© 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. 8-RES_POST_32K-OAI
    11. 8198
    Prev
    Next
    INDEX
    Explanations

    adverbs indicating large changes or impacts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_8.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    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
    316
    +0.09
    0.4%
    474
    +0.09
    0.4%
    243
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    151
    +0.09
    0.05
    117
    +0.09
    0.04
    307
    +0.09
    0.04
    Negative Logits
    afety
    -0.81
    ifully
    -0.81
    tein
    -0.78
    sburgh
    -0.76
    aple
    -0.76
    icip
    -0.75
    fman
    -0.73
    inently
    -0.72
    ydia
    -0.69
    nery
    -0.69
    POSITIVE LOGITS
     impacting
    0.92
     impacted
    0.92
     outnumbered
    0.89
     underest
    0.88
     effected
    0.87
     reduced
    0.82
     understatement
    0.80
     reduce
    0.78
     altered
    0.76
     uptick
    0.74
    Activations Density 0.121%

    No Known Activations