© 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. 8851
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to organizational founding and establishment

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    125
    +0.09
    0.4%
    205
    +0.08
    0.4%
    612
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    665
    +0.09
    0.07
    295
    +0.08
    0.04
    725
    +0.08
    0.04
    Negative Logits
    Kin
    -0.66
     toile
    -0.64
     Surface
    -0.63
     ton
    -0.63
    warm
    -0.59
    wash
    -0.59
     reuse
    -0.59
     withheld
    -0.58
    channelAvailability
    -0.58
     shove
    -0.57
    POSITIVE LOGITS
    ablished
    0.82
    ateurs
    0.80
    okane
    0.74
    quartered
    0.74
    ename
    0.72
    October
    0.72
     1974
    0.71
    elvet
    0.71
     1976
    0.71
    rative
    0.70
    Activations Density 0.509%

    No Known Activations