© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    5. GPT2-Small
    7. Residual Post - 32k
    9. 8-RES_POST_32K-OAI
    11. 8763
    Prev
    Next
    INDEX
    Explanations

    financial terms and references to economic conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_8.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    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
    87
    +0.20
    1.0%
    64
    +0.20
    1.0%
    314
    +0.14
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    718
    +0.20
    0.23
    526
    +0.20
    -0.16
    8
    +0.14
    0.16
    Negative Logits
    ymm
    -0.56
     POLITICO
    -0.54
     Eagles
    -0.52
     Pog
    -0.52
    resa
    -0.51
     Trafford
    -0.51
     KL
    -0.50
     UCH
    -0.50
    nesota
    -0.49
     Berks
    -0.49
    POSITIVE LOGITS
     respectively
    0.91
    etheless
    0.86
    èĢ
    0.74
    )).
    0.67
     ç¥ŀ
    0.65
    ]).
    0.65
    çī
    0.65
     eleph
    0.63
     latter
    0.62
    NetMessage
    0.61
    Activations Density 24.576%

    No Known Activations