© 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. 27104
    Prev
    Next
    INDEX
    Explanations

    references to political authority or governance

    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
    658
    +0.13
    0.6%
    454
    +0.11
    0.5%
    499
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    658
    +0.13
    0.06
    288
    +0.11
    0.07
    499
    +0.10
    0.03
    Negative Logits
    pring
    -0.73
     Reply
    -0.67
     supra
    -0.64
    uers
    -0.64
    ubi
    -0.63
    ument
    -0.62
    inters
    -0.60
    ourney
    -0.60
    iflower
    -0.60
    ultane
    -0.58
    POSITIVE LOGITS
     ausp
    1.43
     supervision
    1.35
     guise
    1.35
     microscope
    1.22
     circumstances
    1.20
     umbrella
    1.17
     conditions
    1.10
     banner
    1.08
     canopy
    0.91
     pretext
    0.90
    Activations Density 1.055%

    No Known Activations