© 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. 29882
    Prev
    Next
    INDEX
    Explanations

    references to U.S. government entities and their actions

    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%
    506
    +0.11
    0.5%
    287
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.11
    0.04
    136
    +0.11
    0.04
    228
    +0.10
    0.04
    Negative Logits
    edience
    -0.62
     enqu
    -0.61
    ption
    -0.60
     oppressed
    -0.59
     delegated
    -0.59
     essentials
    -0.58
     manifesto
    -0.58
     fuck
    -0.57
     Notting
    -0.57
     atom
    -0.57
    POSITIVE LOGITS
    Justice
    0.76
    Va
    0.74
    zbek
    0.73
    yers
    0.72
    ahoo
    0.72
     Justice
    0.72
    lly
    0.71
    sburgh
    0.69
    Web
    0.69
     Telecom
    0.67
    Activations Density 0.518%

    No Known Activations