© 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. 28460
    Prev
    Next
    INDEX
    Explanations

    the phrase "one of" or variations indicating a significant position or ranking

    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
    373
    +0.12
    0.6%
    530
    +0.12
    0.5%
    89
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    697
    +0.12
    0.05
    693
    +0.12
    0.06
    557
    +0.09
    0.05
    Negative Logits
    osponsors
    -0.89
    ittees
    -0.78
    raid
    -0.76
    ples
    -0.74
    isons
    -0.69
     externalToEVAOnly
    -0.67
    ptoms
    -0.66
    ollower
    -0.61
    ption
    -0.60
    mons
    -0.59
    POSITIVE LOGITS
     Europe
    0.98
     America
    0.98
    America
    0.92
     Asia
    0.81
     humankind
    0.79
     Britain
    0.78
    Britain
    0.77
     Africa
    0.76
     world
    0.75
     Canada
    0.74
    Activations Density 0.167%

    No Known Activations