© 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. 30085
    Prev
    Next
    INDEX
    Explanations

    conversational phrases and expressions of agreement or acknowledgment

    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
    218
    +0.11
    0.5%
    219
    +0.09
    0.4%
    188
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    267
    +0.11
    0.07
    496
    +0.09
    0.05
    6
    +0.09
    0.06
    Negative Logits
    eday
    -0.80
    ļéĨĴ
    -0.79
    forth
    -0.74
    ember
    -0.70
    ++++++++++++++++
    -0.70
    âķIJâķIJ
    -0.69
     sacrific
    -0.68
    Purchase
    -0.68
    ש
    -0.67
     undertake
    -0.67
    POSITIVE LOGITS
     Interesting
    1.15
    yeah
    1.13
     Sounds
    0.97
    Yeah
    0.96
    Sounds
    0.94
     Weird
    0.92
    interesting
    0.91
     Yeah
    0.87
     funny
    0.87
    well
    0.87
    Activations Density 0.322%

    No Known Activations