© 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. 30563
    Prev
    Next
    INDEX
    Explanations

    phrases conveying a sense of impending action or change

    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
    683
    +0.12
    0.6%
    282
    +0.11
    0.5%
    178
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    720
    +0.12
    0.14
    297
    +0.11
    0.10
    43
    +0.10
    0.09
    Negative Logits
    emale
    -0.82
     MFT
    -0.77
    aeda
    -0.74
    ormal
    -0.74
    UTC
    -0.73
    bilt
    -0.73
    天
    -0.72
    姫
    -0.72
    PDATED
    -0.72
    riminal
    -0.71
    POSITIVE LOGITS
     wondering
    1.26
     imagining
    1.17
     remembering
    1.06
     afraid
    1.04
     thinking
    1.02
     gazing
    1.00
     forgetting
    0.98
     disbelief
    0.97
     stares
    0.96
     clutching
    0.96
    Activations Density 0.872%

    No Known Activations