© 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. 10-RES_POST_32K-OAI
    11. 30038
    Prev
    Next
    INDEX
    Explanations

    pronouns and references to individuals' feelings and actions

    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
    571
    +0.12
    0.6%
    135
    +0.11
    0.5%
    702
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    139
    +0.12
    0.13
    551
    +0.11
    0.11
    354
    +0.11
    0.10
    Negative Logits
    Ñı
    -0.72
    escription
    -0.68
    oka
    -0.65
    yy
    -0.63
    utenberg
    -0.61
    ORK
    -0.57
    yne
    -0.57
     Mara
    -0.56
    obyl
    -0.56
     Rocks
    -0.54
    POSITIVE LOGITS
     deem
    0.95
     deems
    0.94
     feel
    0.93
     KNOW
    0.91
     feels
    0.85
     knowing
    0.83
     felt
    0.83
     sensed
    0.83
     know
    0.81
     perce
    0.80
    Activations Density 0.715%

    No Known Activations