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

    Neuronpedia

    Jacobian LensNEW
    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. 28723
    Prev
    Next
    INDEX
    Explanations

    solutions and statements about individuals or characters in various contexts

    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
    314
    +0.28
    1.3%
    747
    +0.09
    0.4%
    436
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    139
    +0.28
    0.14
    354
    +0.09
    0.10
    55
    +0.09
    0.10
    Negative Logits
     sizeof
    -0.66
     anten
    -0.65
     ___
    -0.65
     remission
    -0.63
     Punjab
    -0.62
     Rails
    -0.61
     ADS
    -0.61
     Aura
    -0.61
     TBA
    -0.61
     Drupal
    -0.61
    POSITIVE LOGITS
    ldon
    1.25
    pherd
    1.20
    aling
    1.17
    ila
    1.12
    cks
    1.09
    isen
    1.08
    gemony
    1.07
    aler
    1.06
    lly
    1.03
    avier
    1.03
    Activations Density 1.179%

    No Known Activations