Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Residual Post - 32k
    5. 6-RES_POST_32K-OAI
    6. 4206
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "ginger" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_6.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    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
    178
    +0.14
    0.6%
    385
    +0.10
    0.5%
    459
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.14
    0.02
    288
    +0.10
    0.03
    548
    +0.10
    0.02
    Negative Logits
    renheit
    -0.76
    Ö¼
    -0.76
    NRS
    -0.76
    veland
    -0.70
    FontSize
    -0.69
    zzi
    -0.69
    merce
    -0.67
    aucuses
    -0.66
    abilities
    -0.66
    gur
    -0.62
    POSITIVE LOGITS
    icum
    0.97
    isms
    0.96
    omics
    0.94
    alia
    0.92
    swick
    0.91
    rawn
    0.89
    anth
    0.86
    alyst
    0.85
    beard
    0.84
    istically
    0.82
    Activations Density 0.059%

    No Known Activations