© 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. 10-RES_POST_32K-OAI
    11. 26524
    Prev
    Next
    INDEX
    Explanations

    phrases related to evading accountability or consequences

    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
    314
    +0.12
    0.5%
    690
    +0.12
    0.5%
    423
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    665
    +0.12
    0.03
    761
    +0.12
    0.03
    533
    +0.10
    0.03
    Negative Logits
     Emer
    -0.69
    ledge
    -0.66
    Emer
    -0.62
     Haley
    -0.60
    Lens
    -0.60
    Interstitial
    -0.59
     Corps
    -0.59
    cham
    -0.59
     Echo
    -0.58
     Generations
    -0.58
    POSITIVE LOGITS
     unsc
    1.07
     okay
    0.80
     alright
    0.78
     easy
    0.77
     easier
    0.74
    ouri
    0.71
    rm
    0.70
    sa
    0.69
    ivated
    0.68
    retty
    0.68
    Activations Density 0.333%

    No Known Activations