© 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 EvalsExportsinterp-engineNEWAPI 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. 32269
    Prev
    Next
    INDEX
    Explanations

    expressions related to physical and mental well-being

    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
    610
    +0.16
    0.7%
    373
    +0.13
    0.6%
    638
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    271
    +0.16
    0.11
    759
    +0.13
    0.09
    762
    +0.12
    0.11
    Negative Logits
     cascade
    -0.71
    enge
    -0.69
    iosyncr
    -0.67
    nih
    -0.67
    trump
    -0.66
    href
    -0.66
     casc
    -0.65
     obscure
    -0.64
     fallacy
    -0.62
    gemony
    -0.60
    POSITIVE LOGITS
     physically
    1.01
     mentally
    0.99
     financially
    0.96
     academ
    0.94
     emotionally
    0.89
     spiritually
    0.88
     psychologically
    0.88
     recovering
    0.88
     afterward
    0.86
     afterwards
    0.82
    Activations Density 1.160%

    No Known Activations