© 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. 10-RES_POST_32K-OAI
    11. 28724
    Prev
    Next
    INDEX
    Explanations

    references to journalism and media interactions

    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
    347
    +0.11
    0.5%
    488
    +0.09
    0.4%
    122
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    679
    +0.11
    0.18
    680
    +0.09
    0.04
    554
    +0.08
    -0.03
    Negative Logits
    borgh
    -0.73
    nants
    -0.71
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.71
    amac
    -0.71
    ukong
    -0.69
     cooldown
    -0.68
    ECD
    -0.66
     necklace
    -0.66
    ciation
    -0.66
    aimon
    -0.65
    POSITIVE LOGITS
     journalism
    1.87
     journalistic
    1.75
     reporters
    1.74
     Pulitzer
    1.71
     editorial
    1.70
     Journalism
    1.69
     journalists
    1.68
     editors
    1.68
     Journalists
    1.61
     reporting
    1.60
    Activations Density 7.550%

    No Known Activations