© 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. 29331
    Prev
    Next
    INDEX
    Explanations

    instances of personal reflections or goals expressed in narrative form

    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
    +0.14
    0.6%
    609
    +0.12
    0.5%
    528
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    6
    +0.14
    0.25
    145
    +0.12
    0.20
    622
    +0.10
    0.15
    Negative Logits
     yourselves
    -1.09
     ours
    -0.97
     me
    -0.94
     oneself
    -0.93
     ourselves
    -0.90
     us
    -0.89
     yourself
    -0.80
     myself
    -0.80
     mine
    -0.69
     themselves
    -0.68
    POSITIVE LOGITS
    ãĤ´ãĥ³
    0.92
     Ended
    0.86
     Returning
    0.78
    Playing
    0.76
     Spending
    0.75
    sequent
    0.74
    sequently
    0.73
    etermined
    0.73
    ãĥ¼ãĥ³
    0.72
     Being
    0.71
    Activations Density 2.421%

    No Known Activations