© 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. 8759
    Prev
    Next
    INDEX
    Explanations

    instances of the word "so" indicating causation or emphasis in statements

    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
    348
    +0.10
    0.5%
    572
    +0.10
    0.5%
    8
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    348
    +0.10
    0.02
    521
    +0.10
    0.01
    485
    +0.09
    0.01
    Negative Logits
    IOR
    -0.65
    nesday
    -0.63
     Feld
    -0.63
    jab
    -0.63
    lif
    -0.62
    Dur
    -0.59
    Library
    -0.57
    RL
    -0.56
    Js
    -0.56
    Kids
    -0.56
    POSITIVE LOGITS
    ommel
    0.67
    odi
    0.64
    ivot
    0.62
    oros
    0.60
    ,
    0.60
     Sponsor
    0.56
    appa
    0.56
    soDeliveryDate
    0.56
    ,...
    0.55
     Guest
    0.55
    Activations Density 0.078%

    No Known Activations