© 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. 10-RES_POST_32K-OAI
    11. 28056
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "Enter"

    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
    314
    +0.13
    0.6%
    683
    +0.11
    0.5%
    45
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    284
    +0.13
    0.01
    184
    +0.11
    0.01
    206
    +0.10
    0.01
    Negative Logits
     apart
    -0.71
    ecause
    -0.70
    ometimes
    -0.62
     disadvant
    -0.60
     Lange
    -0.59
     Hut
    -0.58
     Arms
    -0.57
     bonded
    -0.57
     peaks
    -0.57
     mornings
    -0.56
    POSITIVE LOGITS
    prise
    1.89
    tainment
    1.65
    prises
    1.63
    taining
    1.47
    tain
    1.42
    prising
    1.34
    tained
    1.21
    TAIN
    1.10
    tains
    0.87
    ocol
    0.83
    Activations Density 0.175%

    No Known Activations