© 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. 32285
    Prev
    Next
    INDEX
    Explanations

    phrases related to defending opinions or actions

    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
    329
    +0.10
    0.4%
    679
    +0.09
    0.4%
    604
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    507
    +0.10
    0.04
    516
    +0.09
    0.03
    679
    +0.09
    0.04
    Negative Logits
    ptoms
    -0.69
    ombies
    -0.67
     NEWS
    -0.65
    OTOS
    -0.65
    problem
    -0.64
    emi
    -0.63
    oters
    -0.62
     ILCS
    -0.61
     distraction
    -0.61
    psy
    -0.60
    POSITIVE LOGITS
     against
    1.23
    against
    1.09
     Against
    1.00
     vigorously
    0.97
     indef
    0.94
     forcefully
    0.85
    ably
    0.85
     vehemently
    0.83
    orously
    0.80
    Against
    0.78
    Activations Density 0.443%

    No Known Activations