© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    5. GPT2-Small
    7. Residual Post - 32k
    9. 10-RES_POST_32K-OAI
    11. 29447
    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 @ 10-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_10.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    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
    +0.13
    0.6%
    439
    +0.11
    0.5%
    712
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    439
    +0.13
    0.02
    255
    +0.11
    0.02
    737
    +0.11
    0.01
    Negative Logits
     Majesty
    -0.71
    asting
    -0.71
    osterone
    -0.69
    asted
    -0.67
    iets
    -0.64
    undy
    -0.59
    Sham
    -0.59
    onne
    -0.58
    avorite
    -0.57
    owl
    -0.56
    POSITIVE LOGITS
    fully
    1.68
    ful
    1.32
    lessness
    1.29
    fulness
    1.19
    lessly
    1.05
    less
    0.99
    sworth
    0.93
    FUL
    0.92
    full
    0.91
    ual
    0.87
    Activations Density 0.060%

    No Known Activations