© 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
    2. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Residual Post - 32k
    5. 10-RES_POST_32K-OAI
    6. 31112
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize the concept of obligation or missed opportunities

    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
    551
    +0.12
    0.6%
    505
    +0.12
    0.5%
    699
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    566
    +0.12
    0.06
    344
    +0.12
    0.05
    7
    +0.11
    0.04
    Negative Logits
     Cth
    -0.63
     deterioration
    -0.61
     contradictions
    -0.61
     impressive
    -0.59
    esses
    -0.57
     embodiments
    -0.57
     Science
    -0.56
     extraordinary
    -0.56
    ingen
    -0.56
     shortcomings
    -0.56
    POSITIVE LOGITS
     guessed
    0.85
     known
    0.85
     waited
    0.84
     Known
    0.80
    ran
    0.77
     yelled
    0.74
     listened
    0.73
     liked
    0.73
     stayed
    0.72
    ascript
    0.71
    Activations Density 0.166%

    No Known Activations