© 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
    3. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    5. GPT2-Small
    7. Residual Post - 32k
    9. 8-RES_POST_32K-OAI
    11. 5833
    Prev
    Next
    INDEX
    Explanations

    terms related to contradictions and criticisms

    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
    596
    +0.10
    0.4%
    628
    +0.09
    0.4%
    329
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    724
    +0.10
    0.12
    271
    +0.09
    0.07
    737
    +0.09
    0.09
    Negative Logits
    ewitness
    -0.74
    thia
    -0.72
    xit
    -0.72
    Ħ¢
    -0.67
    und
    -0.67
    ousands
    -0.67
    uine
    -0.67
    ļéĨĴ
    -0.67
    =""
    -0.66
    ]=
    -0.65
    POSITIVE LOGITS
     considering
    1.03
     nowadays
    1.00
     compared
    0.95
     lately
    0.90
     anyways
    0.85
     dudes
    0.80
     huh
    0.79
     haha
    0.78
     judging
    0.77
     alright
    0.75
    Activations Density 1.792%

    No Known Activations