© 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 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. 29205
    Prev
    Next
    INDEX
    Explanations

    metrics related to approval ratings and economic performance indicators

    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
    +0.11
    0.5%
    724
    +0.10
    0.4%
    488
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    724
    +0.11
    0.11
    540
    +0.10
    0.10
    542
    +0.10
    0.09
    Negative Logits
     redes
    -0.68
    çīĪ
    -0.67
    wolf
    -0.65
    itives
    -0.63
     reusable
    -0.63
     foreskin
    -0.61
     learns
    -0.58
     manufact
    -0.57
     gladly
    -0.56
    DCS
    -0.56
    POSITIVE LOGITS
     lows
    1.02
     amid
    0.97
    despite
    0.88
     highs
    0.85
     topped
    0.81
     exceeding
    0.80
     plateau
    0.80
     despite
    0.80
    emic
    0.80
     peaked
    0.78
    Activations Density 0.934%

    No Known Activations