© 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. 31966
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to accessibility and openness

    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
    134
    +0.13
    0.6%
    281
    +0.11
    0.5%
    0
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.13
    0.09
    76
    +0.11
    0.06
    0
    +0.11
    0.05
    Negative Logits
    anners
    -0.78
    conom
    -0.72
    aurus
    -0.72
    tle
    -0.68
    atoes
    -0.67
    jong
    -0.67
    birds
    -0.64
    ventory
    -0.64
    asty
    -0.63
    terness
    -0.62
    POSITIVE LOGITS
     insured
    1.06
     uninsured
    0.93
     unrestricted
    0.92
     unregulated
    0.92
     certified
    0.91
     operated
    0.86
     unpop
    0.86
     uninterrupted
    0.85
     nonpartisan
    0.85
     supervised
    0.84
    Activations Density 1.159%

    No Known Activations