© 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. 5575
    Prev
    Next
    INDEX
    Explanations

    words associated with harshness and criticism

    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
    707
    +0.09
    0.4%
    461
    +0.09
    0.4%
    755
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.09
    0.03
    659
    +0.09
    0.02
    284
    +0.09
    0.02
    Negative Logits
    erers
    -0.79
     Canal
    -0.75
    brates
    -0.74
    ually
    -0.71
    llers
    -0.70
    bal
    -0.69
    trak
    -0.67
    brate
    -0.67
    erer
    -0.66
     Cay
    -0.66
    POSITIVE LOGITS
    ongyang
    0.79
    ower
    0.77
    anasia
    0.72
    azines
    0.71
    Ö¼
    0.69
     Throne
    0.69
    inite
    0.69
    omatic
    0.69
    otten
    0.68
    atan
    0.68
    Activations Density 0.136%

    No Known Activations