© 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. 10-RES_POST_32K-OAI
    11. 28867
    Prev
    Next
    INDEX
    Explanations

    the conjunction "and" used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_10.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    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
    373
    +0.12
    0.5%
    395
    +0.11
    0.5%
    30
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    576
    +0.12
    0.01
    546
    +0.11
    0.01
    591
    +0.10
    0.01
    Negative Logits
     warr
    -0.75
     glim
    -0.66
     princ
    -0.66
    olor
    -0.63
    LY
    -0.61
    emouth
    -0.58
     streng
    -0.58
     inval
    -0.57
    Brave
    -0.57
    heres
    -0.55
    POSITIVE LOGITS
    uled
    0.75
     again
    0.75
     forget
    0.74
     above
    0.72
    above
    0.71
     over
    0.70
    over
    0.66
    atched
    0.65
     Again
    0.64
    utation
    0.63
    Activations Density 0.121%

    No Known Activations