© 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. 30765
    Prev
    Next
    INDEX
    Explanations

    expressions of social interactions and emotional dynamics

    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
    100
    +0.14
    0.6%
    661
    +0.10
    0.5%
    29
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    6
    +0.14
    0.16
    640
    +0.10
    0.13
    669
    +0.10
    0.08
    Negative Logits
    Had
    -1.02
     depended
    -0.96
     existed
    -0.93
     lacked
    -0.92
     resided
    -0.91
    oided
    -0.90
     benefited
    -0.90
     undertook
    -0.88
     differed
    -0.88
     tended
    -0.85
    POSITIVE LOGITS
     announces
    0.94
     arrives
    0.93
     reaches
    0.93
     begins
    0.92
     emerges
    0.92
     realizes
    0.89
     enters
    0.88
     hangs
    0.88
     Written
    0.88
     asks
    0.86
    Activations Density 2.802%

    No Known Activations