© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 5205
    Prev
    Next
    INDEX
    Explanations

    instances of negation or denial related to significant events or circumstances

    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
    331
    +0.10
    0.5%
    329
    +0.10
    0.5%
    671
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    351
    +0.10
    0.15
    762
    +0.10
    0.20
    221
    +0.10
    0.09
    Negative Logits
     periodically
    -0.63
     assorted
    -0.61
    accompanied
    -0.60
     slowly
    -0.58
     gradually
    -0.56
    rather
    -0.56
     shortly
    -0.56
    ortment
    -0.55
     rather
    -0.54
     occasionally
    -0.52
    POSITIVE LOGITS
     nor
    2.39
     anymore
    2.22
     whatsoever
    1.59
    nor
    1.56
     anything
    1.48
     slightest
    1.47
     any
    1.36
     anybody
    1.33
    yet
    1.29
     anywhere
    1.29
    Activations Density 12.313%

    No Known Activations