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

    Neuronpedia

    Jacobian LensNEW
    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. 28861
    Prev
    Next
    INDEX
    Explanations

    instances of the word "become" and related forms indicating change or transformation

    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
    676
    +0.10
    0.5%
    490
    +0.10
    0.5%
    373
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    7
    +0.10
    0.07
    486
    +0.10
    0.05
    102
    +0.10
    0.07
    Negative Logits
    ysis
    -0.69
    ullivan
    -0.67
     Development
    -0.63
    uez
    -0.62
    aido
    -0.61
    uci
    -0.60
    enary
    -0.60
     CARE
    -0.59
     citiz
    -0.58
     Atk
    -0.58
    POSITIVE LOGITS
     cliché
    1.02
     routine
    0.99
     shorthand
    0.96
     commonplace
    0.89
     normalized
    0.89
     increasingly
    0.86
     synonymous
    0.84
     ingrained
    0.83
     trendy
    0.82
     obsession
    0.79
    Activations Density 0.716%

    No Known Activations