© 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. 29607
    Prev
    Next
    INDEX
    Explanations

    references to statistics or data related to humanitarian issues

    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
    314
    +0.18
    0.8%
    524
    +0.13
    0.6%
    6
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    675
    +0.18
    0.19
    650
    +0.13
    0.20
    314
    +0.12
    0.01
    Negative Logits
     stunts
    -0.74
     incorpor
    -0.74
     fodder
    -0.70
    geries
    -0.70
     manif
    -0.70
     resurrection
    -0.69
     transpl
    -0.68
     harvesting
    -0.68
     township
    -0.68
     accelerated
    -0.68
    POSITIVE LOGITS
    ï¸ı
    2.24
    ï¸
    1.84
    â
    1.31
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    1.31
    âķIJâķIJ
    1.31
    âĪ
    1.30
    âĹ
    1.29
    âĸ
    1.29
    âĶĢâĶĢâĶĢâĶĢ
    1.14
    âķIJ
    1.14
    Activations Density 1.728%

    No Known Activations