© 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. 8-RES_POST_32K-OAI
    11. 5137
    Prev
    Next
    INDEX
    Explanations

    instances of reported speech, particularly the word "said" and its variations

    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
    673
    +0.10
    0.5%
    726
    +0.10
    0.5%
    257
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    514
    +0.10
    0.05
    180
    +0.10
    0.05
    468
    +0.10
    0.05
    Negative Logits
     boycot
    -0.80
     nonviolent
    -0.79
     extremist
    -0.77
     satire
    -0.76
     extremists
    -0.76
     liberals
    -0.71
     cler
    -0.70
     bombard
    -0.70
     prosecutions
    -0.69
     rage
    -0.67
    POSITIVE LOGITS
    ":["
    1.02
    ascript
    0.69
    NBA
    0.69
     backstage
    0.68
     "âĢ¦
    0.66
     Asked
    0.66
    æĪ¦
    0.65
     Regarding
    0.65
     ãĢĮ
    0.65
    yne
    0.64
    Activations Density 0.400%

    No Known Activations