© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 32705
    Prev
    Next
    INDEX
    Explanations

    terms related to support and endorsement, often in a political or social context

    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
    237
    +0.11
    0.5%
    243
    +0.10
    0.5%
    125
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.11
    -0.01
    208
    +0.10
    0.01
    530
    +0.10
    0.01
    Negative Logits
    alus
    -0.78
    aucus
    -0.78
    eneg
    -0.76
    wcs
    -0.75
    aling
    -0.72
    gre
    -0.68
    ensional
    -0.68
    xual
    -0.66
    mite
    -0.66
    ©¶æ
    -0.66
    POSITIVE LOGITS
    INC
    0.66
    omb
    0.64
    othy
    0.59
    Rah
    0.59
     Dreams
    0.58
     por
    0.58
     Pig
    0.58
    stead
    0.58
    aba
    0.57
     mistaken
    0.57
    Activations Density 0.075%

    No Known Activations