© 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. 32620
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "the" and related phrases indicating community or collective experiences

    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
    702
    +0.10
    0.5%
    373
    +0.10
    0.5%
    758
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.10
    0.13
    393
    +0.10
    0.09
    16
    +0.09
    0.05
    Negative Logits
     Sorceress
    -0.78
     Clicker
    -0.71
    dayName
    -0.68
    BIL
    -0.64
    limits
    -0.63
    luster
    -0.61
    Reloaded
    -0.59
    weapons
    -0.59
    Weapons
    -0.58
     rusher
    -0.58
    POSITIVE LOGITS
     audience
    0.92
     whom
    0.91
     vicinity
    0.81
     privileged
    0.76
     attendance
    0.75
     room
    0.74
    who
    0.71
     know
    0.71
     cohort
    0.69
    whose
    0.68
    Activations Density 0.794%

    No Known Activations