© 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. 6838
    Prev
    Next
    INDEX
    Explanations

    the word "in" and its variations or related suffixes

    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
    525
    +0.10
    0.4%
    22
    +0.10
    0.4%
    46
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.10
    0.00
    232
    +0.10
    0.04
    701
    +0.10
    0.03
    Negative Logits
     Falling
    -0.72
     Bett
    -0.63
     dove
    -0.62
     briefs
    -0.61
     maiden
    -0.58
     blazing
    -0.57
     Brill
    -0.57
     partName
    -0.57
    schild
    -0.56
     invis
    -0.56
    POSITIVE LOGITS
    arta
    0.89
    ront
    0.83
    rob
    0.83
    ron
    0.80
    amide
    0.80
    obar
    0.79
    tery
    0.78
    illion
    0.77
    riv
    0.76
    izza
    0.75
    Activations Density 0.287%

    No Known Activations