© 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. 28863
    Prev
    Next
    INDEX
    Explanations

    quantitative expressions and estimates related to population

    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
    +0.16
    0.7%
    126
    +0.10
    0.5%
    464
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    430
    +0.16
    0.08
    655
    +0.10
    0.07
    312
    +0.09
    0.07
    Negative Logits
     Costs
    -0.80
     depreciation
    -0.79
     damages
    -0.73
     profits
    -0.69
     costs
    -0.68
     funds
    -0.68
     PAY
    -0.66
     $$
    -0.66
     purchases
    -0.66
    UTC
    -0.64
    POSITIVE LOGITS
    dozen
    1.21
     dozen
    0.98
     handful
    0.72
    ween
    0.68
     hundred
    0.66
    idae
    0.65
     thousand
    0.64
    iren
    0.64
    lect
    0.64
    esides
    0.64
    Activations Density 0.781%

    No Known Activations