© 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. 29364
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to coefficients and their mathematical 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
    3
    +0.10
    0.4%
    577
    +0.10
    0.4%
    391
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.10
    -0.01
    586
    +0.10
    0.03
    111
    +0.09
    0.02
    Negative Logits
     tremend
    -0.69
    phia
    -0.65
     Pog
    -0.63
     Belle
    -0.61
    cgi
    -0.60
    Quantity
    -0.59
     Panzer
    -0.57
    tube
    -0.57
    Font
    -0.57
    WER
    -0.57
    POSITIVE LOGITS
    rency
    1.35
    workers
    0.81
    ition
    0.81
    cious
    0.81
    incial
    0.77
    operative
    0.76
    hesive
    0.75
    zyme
    0.75
    idence
    0.74
    shed
    0.74
    Activations Density 0.667%

    No Known Activations