© 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. 7035
    Prev
    Next
    INDEX
    Explanations

    conjunctions and phrases that indicate a list or connection

    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
    113
    +0.11
    0.5%
    508
    +0.10
    0.5%
    219
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.11
    0.11
    384
    +0.10
    0.05
    120
    +0.10
    0.07
    Negative Logits
     Voldemort
    -0.68
     Zionism
    -0.68
     imperfect
    -0.68
     Mankind
    -0.66
    èª
    -0.65
    XY
    -0.65
    TEXTURE
    -0.63
     Iranians
    -0.63
     Intent
    -0.63
     Guilty
    -0.63
    POSITIVE LOGITS
     cafes
    1.20
     restaurants
    1.18
     barracks
    1.16
     workplaces
    1.12
     parks
    1.12
     gardens
    1.12
     cafeteria
    1.08
     café
    1.08
     malls
    1.08
     clinics
    1.06
    Activations Density 1.363%

    No Known Activations