© 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. 8940
    Prev
    Next
    INDEX
    Explanations

    references to daily and ordinary experiences

    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
    756
    +0.13
    0.6%
    606
    +0.10
    0.4%
    285
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    132
    +0.13
    0.02
    651
    +0.10
    0.03
    276
    +0.09
    0.03
    Negative Logits
    bid
    -0.88
    apter
    -0.82
    imov
    -0.75
    eln
    -0.74
    etr
    -0.72
    ittal
    -0.71
    aye
    -0.69
    enic
    -0.69
    dinand
    -0.68
    aterasu
    -0.68
    POSITIVE LOGITS
     life
    1.01
     occurrences
    0.94
     lives
    0.92
     existence
    0.90
     routines
    0.86
     everyday
    0.85
     essentials
    0.84
     activities
    0.81
     routine
    0.81
     lifes
    0.81
    Activations Density 0.217%

    No Known Activations