© 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. 32250
    Prev
    Next
    INDEX
    Explanations

    percentages and statistics related to public opinion on social issues

    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
    224
    +0.12
    0.5%
    190
    +0.11
    0.5%
    153
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    139
    +0.12
    0.19
    224
    +0.11
    0.15
    762
    +0.11
    0.17
    Negative Logits
     Clever
    -0.74
    ĸļ
    -0.72
     Cinderella
    -0.72
     Miracle
    -0.71
     Thieves
    -0.69
     Proced
    -0.69
     pandemonium
    -0.67
    luck
    -0.66
     disappearing
    -0.65
    itary
    -0.64
    POSITIVE LOGITS
     opposes
    1.52
     oppose
    1.43
     endorse
    1.39
     support
    1.38
     supports
    1.38
     opposed
    1.37
     supported
    1.30
     favor
    1.28
     sided
    1.24
     sympath
    1.24
    Activations Density 2.338%

    No Known Activations