© 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. 5230
    Prev
    Next
    INDEX
    Explanations

    the variations of the word "te" in various contexts

    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
    373
    +0.11
    0.5%
    659
    +0.11
    0.5%
    493
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.11
    0.03
    631
    +0.11
    0.03
    420
    +0.10
    0.03
    Negative Logits
     IMAGES
    -0.71
     Loren
    -0.68
    naire
    -0.66
     macros
    -0.63
     Constantin
    -0.61
     ANGEL
    -0.60
    ĸļ
    -0.60
     Wikimedia
    -0.59
    istics
    -0.59
    ervatives
    -0.58
    POSITIVE LOGITS
    legraph
    1.04
    legram
    1.01
    eming
    0.86
    aming
    0.82
    pees
    0.81
    ared
    0.81
    aky
    0.79
    cc
    0.78
    gged
    0.78
    ccess
    0.78
    Activations Density 0.040%

    No Known Activations