© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 8733
    Prev
    Next
    INDEX
    Explanations

    interrogative phrases that inquire about a location or situation

    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
    496
    +0.14
    0.7%
    373
    +0.14
    0.6%
    585
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    236
    +0.14
    0.04
    300
    +0.14
    0.04
    186
    +0.13
    0.03
    Negative Logits
     easing
    -0.70
     showing
    -0.64
     unlocking
    -0.61
     lifting
    -0.60
     gripping
    -0.60
    interstitial
    -0.58
     circulation
    -0.58
     capturing
    -0.56
     guiActiveUnfocused
    -0.56
     portraying
    -0.56
    POSITIVE LOGITS
    ver
    1.11
    fore
    0.96
    abouts
    0.96
    endale
    0.81
    onga
    0.77
     Are
    0.73
    anan
    0.72
    alth
    0.71
     Does
    0.70
    arth
    0.70
    Activations Density 0.065%

    No Known Activations