© 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. 29829
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "launch" and its variations 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
    541
    +0.10
    0.4%
    665
    +0.10
    0.4%
    696
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    665
    +0.10
    0.05
    725
    +0.10
    0.03
    541
    +0.10
    0.04
    Negative Logits
    abling
    -0.67
    ertodd
    -0.62
    rous
    -0.61
    enhagen
    -0.60
     +/-
    -0.57
    arov
    -0.56
    oping
    -0.56
    olin
    -0.55
    Joined
    -0.55
    iquid
    -0.55
    POSITIVE LOGITS
     INTO
    1.03
     into
    1.03
     Into
    0.93
     anew
    0.88
     raids
    0.85
     hostilities
    0.84
     probes
    0.83
     tir
    0.80
     campaigns
    0.80
     missiles
    0.80
    Activations Density 0.481%

    No Known Activations