© 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. 29875
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "list" 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
    642
    +0.11
    0.5%
    80
    +0.11
    0.5%
    610
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.11
    -0.00
    558
    +0.11
    0.02
    609
    +0.11
    0.03
    Negative Logits
    ILS
    -0.70
    cules
    -0.67
    æĪ¦
    -0.66
    phrine
    -0.66
     Merrill
    -0.66
     AMERICA
    -0.65
     Crosby
    -0.62
    0000000
    -0.62
    BIP
    -0.57
    YP
    -0.57
    POSITIVE LOGITS
    ener
    1.43
    ening
    1.42
    eners
    1.25
    ened
    1.19
    ens
    1.16
    en
    1.11
    EN
    1.00
    uce
    0.94
    enth
    0.90
    enable
    0.89
    Activations Density 0.262%

    No Known Activations