© 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 EvalsExportsinterp-engineNEWAPI 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. 7411
    Prev
    Next
    INDEX
    Explanations

    instances of the word "thus" 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
    132
    +0.12
    0.5%
    55
    +0.11
    0.5%
    580
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    155
    +0.12
    0.02
    580
    +0.11
    0.02
    655
    +0.10
    0.02
    Negative Logits
     Polo
    -0.64
     Mehran
    -0.57
     Ones
    -0.56
    kick
    -0.55
     anten
    -0.52
     Boulder
    -0.51
     Kem
    -0.51
     Greenwich
    -0.51
     AAA
    -0.51
     Wander
    -0.51
    POSITIVE LOGITS
     far
    1.16
    forth
    1.14
    far
    1.09
    ly
    0.96
    entimes
    0.88
    forward
    0.87
    fully
    0.82
    bered
    0.80
    apy
    0.78
    lessly
    0.77
    Activations Density 0.039%

    No Known Activations