© 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. 32011
    Prev
    Next
    INDEX
    Explanations

    concepts related to self-worth and personal improvement

    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
    373
    +0.14
    0.6%
    695
    +0.11
    0.5%
    445
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    737
    +0.14
    0.07
    271
    +0.11
    0.07
    759
    +0.09
    0.06
    Negative Logits
     hemor
    -0.72
     leukemia
    -0.64
     deteriorating
    -0.61
    NetMessage
    -0.59
    uga
    -0.58
     numbering
    -0.57
     narrowing
    -0.57
     refurb
    -0.57
     fracturing
    -0.56
     pecul
    -0.56
    POSITIVE LOGITS
     oneself
    1.28
     yourself
    0.95
     ourselves
    0.89
     Yourself
    0.88
     selves
    0.83
     yourselves
    0.83
     forever
    0.77
     bearer
    0.71
     again
    0.69
    parent
    0.67
    Activations Density 1.881%

    No Known Activations