© 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. 30141
    Prev
    Next
    INDEX
    Explanations

    indicators of economic performance and stability

    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
    408
    +0.12
    0.5%
    5
    +0.10
    0.5%
    368
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.12
    0.11
    408
    +0.10
    0.11
    720
    +0.10
    0.09
    Negative Logits
    fell
    -0.83
    wark
    -0.74
    icus
    -0.74
    ovember
    -0.70
    oti
    -0.69
    opol
    -0.69
    ocument
    -0.68
    Enlarge
    -0.68
    berman
    -0.67
    quer
    -0.67
    POSITIVE LOGITS
     ample
    1.44
     abundant
    1.30
     excellent
    1.28
     impecc
    1.25
     lousy
    1.23
     plentiful
    1.21
     plenty
    1.21
     generous
    1.20
     strong
    1.19
     decent
    1.17
    Activations Density 1.346%

    No Known Activations