© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 29816
    Prev
    Next
    INDEX
    Explanations

    the repetition of the word "at" and variations of its usage in context

    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
    736
    +0.10
    0.5%
    425
    +0.10
    0.4%
    492
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    611
    +0.10
    0.06
    467
    +0.10
    0.05
    62
    +0.10
    0.06
    Negative Logits
     Skydragon
    -0.70
     Dunk
    -0.70
     Mald
    -0.64
     Luxembourg
    -0.61
    76561
    -0.60
     TAG
    -0.59
    wik
    -0.59
     Winc
    -0.59
    /?
    -0.59
    workshop
    -0.58
    POSITIVE LOGITS
     least
    1.14
     root
    0.72
    one
    0.71
     longest
    0.71
    hemy
    0.70
    actly
    0.70
    hem
    0.70
    hal
    0.70
     essence
    0.70
    ones
    0.69
    Activations Density 0.236%

    No Known Activations