© 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. 8727
    Prev
    Next
    INDEX
    Explanations

    references to the concept of meaning

    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
    642
    +0.14
    0.7%
    712
    +0.11
    0.5%
    688
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    642
    +0.14
    0.02
    439
    +0.11
    0.01
    178
    +0.10
    0.02
    Negative Logits
    osterone
    -0.72
    nih
    -0.66
    asting
    -0.63
    Sham
    -0.60
    asted
    -0.60
    iets
    -0.60
    aliation
    -0.58
     Frazier
    -0.58
    thumbnails
    -0.57
    Hay
    -0.56
    POSITIVE LOGITS
    fully
    1.59
    ful
    1.24
    lessness
    1.17
    fulness
    1.13
    sworth
    0.97
    lessly
    0.91
    psons
    0.89
    FUL
    0.88
    staking
    0.86
    ual
    0.82
    Activations Density 0.036%

    No Known Activations