© 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. 10-RES_POST_32K-OAI
    6. 29492
    Prev
    Next
    INDEX
    Explanations

    negative sentiment or expressions of disappointment

    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
    442
    +0.14
    0.6%
    639
    +0.13
    0.6%
    640
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    639
    +0.14
    0.01
    442
    +0.13
    0.02
    430
    +0.09
    0.01
    Negative Logits
     embattled
    -0.74
     navigating
    -0.74
     Dickinson
    -0.73
     sponsoring
    -0.72
     mathemat
    -0.72
     licking
    -0.71
     pesky
    -0.71
     Ange
    -0.69
     cler
    -0.69
     thous
    -0.69
    POSITIVE LOGITS
    TI
    1.32
    0200
    1.16
    4000
    1.15
    050
    1.12
    6000
    1.09
    1800
    1.07
    6666
    1.06
    3000
    1.03
    05
    1.03
    CHAT
    1.03
    Activations Density 0.053%

    No Known Activations