© 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. 31138
    Prev
    Next
    INDEX
    Explanations

    numeric values and their relationships to quantities or measurements

    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
    640
    +0.23
    1.1%
    314
    +0.17
    0.8%
    6
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.23
    0.09
    160
    +0.17
    0.07
    107
    +0.12
    0.07
    Negative Logits
    hement
    -0.90
     destro
    -0.90
     answ
    -0.85
    ogun
    -0.84
     seiz
    -0.83
     mathemat
    -0.82
     occas
    -0.81
     rul
    -0.79
     lawy
    -0.79
     prosec
    -0.79
    POSITIVE LOGITS
    ³³³³³³³³
    1.83
    ³³³³
    1.54
    ³³³
    1.49
    ³³
    1.46
    ³³³³³³³³³³³³³³³³
    1.46
    Âł
    1.25
    ↵Âł
    1.06
    Anonymous
    1.04
    Anyway
    1.01
    Posted
    0.99
    Activations Density 0.167%

    No Known Activations