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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Residual Post - 32k
    5. 8-RES_POST_32K-OAI
    6. 4538
    Prev
    Next
    INDEX
    Explanations

    references to democracy and the political process

    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
    373
    +0.17
    0.8%
    760
    +0.10
    0.5%
    309
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    760
    +0.17
    0.03
    373
    +0.10
    -0.03
    610
    +0.09
    0.02
    Negative Logits
    CONCLUS
    -0.74
     ..."
    -0.71
     incent
    -0.69
     ._
    -0.68
    ãĤ¦ãĤ¹
    -0.68
     acknow
    -0.68
     [&
    -0.67
     ........
    -0.67
    ilitarian
    -0.67
     tho
    -0.66
    POSITIVE LOGITS
    radio
    0.81
     VICE
    0.80
     Jazeera
    0.73
     Transcript
    0.73
     GOODMAN
    0.72
     Democracy
    0.69
    Fight
    0.68
     NPR
    0.64
    edition
    0.64
    VICE
    0.63
    Activations Density 0.631%

    No Known Activations