© 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 EvalsExportsinterp-engineNEWAPI 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. 26699
    Prev
    Next
    INDEX
    Explanations

    references to government authority and power dynamics

    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
    665
    +0.12
    0.6%
    453
    +0.10
    0.5%
    592
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    86
    +0.12
    0.13
    665
    +0.10
    0.14
    139
    +0.09
    0.13
    Negative Logits
    vity
    -0.77
    ftime
    -0.73
    ortun
    -0.73
     remem
    -0.72
     Horizons
    -0.71
    lehem
    -0.70
    luck
    -0.68
     Avg
    -0.67
    phies
    -0.65
     VIDEOS
    -0.65
    POSITIVE LOGITS
     confisc
    1.31
     arbitrarily
    1.28
     unilaterally
    1.24
     unconstitutional
    1.23
     coerc
    1.18
     legisl
    1.17
     forcibly
    1.15
     outlawed
    1.15
     outlaw
    1.14
     imposing
    1.12
    Activations Density 2.796%

    No Known Activations