© 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. 31846
    Prev
    Next
    INDEX
    Explanations

    elements related to conflicts and rivalries in narratives

    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
    324
    +0.09
    0.4%
    383
    +0.09
    0.4%
    132
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.09
    0.13
    575
    +0.09
    0.12
    225
    +0.09
    0.11
    Negative Logits
    TPPStreamerBot
    -0.71
     certific
    -0.70
     unequiv
    -0.66
     palp
    -0.65
     specificity
    -0.65
     aust
    -0.64
    riott
    -0.62
     WEEK
    -0.62
    orient
    -0.62
     breadth
    -0.62
    POSITIVE LOGITS
    .[
    1.02
     disguised
    1.02
     Luffy
    0.94
     aboard
    0.90
    ,[
    0.89
     Shinra
    0.89
     Cerberus
    0.86
     Luthor
    0.86
     mutated
    0.86
     Metatron
    0.85
    Activations Density 1.741%

    No Known Activations