© 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. 8-RES_POST_32K-OAI
    11. 4364
    Prev
    Next
    INDEX
    Explanations

    mentions of various governmental regimes, particularly in a negative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_8.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    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
    488
    +0.18
    0.8%
    288
    +0.14
    0.6%
    706
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    488
    +0.18
    0.02
    146
    +0.14
    0.02
    288
    +0.09
    0.02
    Negative Logits
     Lent
    -0.79
    ritch
    -0.73
     Voy
    -0.72
     Ness
    -0.70
     Niet
    -0.70
    Universal
    -0.67
    Pokemon
    -0.66
     Spiel
    -0.66
     Blessed
    -0.66
    furt
    -0.65
    POSITIVE LOGITS
     regimes
    0.79
    idency
    0.74
     overthrow
    0.74
    archs
    0.71
    ocre
    0.71
     regime
    0.70
     governing
    0.70
    lict
    0.70
     administ
    0.69
    wide
    0.67
    Activations Density 0.052%

    No Known Activations