© 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. 8-RES_POST_32K-OAI
    11. 5129
    Prev
    Next
    INDEX
    Explanations

    technical terms and references related to patents

    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
    697
    +0.12
    0.6%
    373
    +0.11
    0.5%
    313
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    435
    +0.12
    0.02
    642
    +0.11
    0.04
    22
    +0.09
    0.03
    Negative Logits
    partisan
    -0.75
     quota
    -0.69
     exile
    -0.68
     referendum
    -0.68
     Politics
    -0.68
     quotas
    -0.66
     Erit
    -0.66
    govtrack
    -0.66
    vernment
    -0.65
    Poll
    -0.64
    POSITIVE LOGITS
     embodiments
    1.31
     FIG
    1.27
     embodiment
    1.12
    FIG
    1.10
     invention
    1.01
     patent
    0.92
    ENTION
    0.88
     inventions
    0.86
    empl
    0.84
     herein
    0.83
    Activations Density 0.554%

    No Known Activations