© 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. 32651
    Prev
    Next
    INDEX
    Explanations

    phrases or concepts associated with the concept of 'front-runners' in various contexts

    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
    +0.13
    0.6%
    698
    +0.13
    0.6%
    537
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    152
    +0.13
    0.05
    314
    +0.13
    0.01
    537
    +0.10
    0.03
    Negative Logits
     mediation
    -0.71
     ult
    -0.70
     patience
    -0.64
    »Ĵ
    -0.64
     pen
    -0.64
     pow
    -0.64
     renew
    -0.63
     confidence
    -0.62
     postp
    -0.61
     deposition
    -0.61
    POSITIVE LOGITS
    facing
    1.42
    mounted
    1.14
    eye
    1.07
    side
    1.07
    panel
    1.05
    quartered
    1.03
    row
    1.03
    ported
    1.03
    turned
    1.01
    door
    1.01
    Activations Density 0.207%

    No Known Activations