© 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. 8-RES_POST_32K-OAI
    11. 6753
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing contrast or reluctance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_8.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    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
    172
    +0.12
    0.5%
    251
    +0.10
    0.5%
    733
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    718
    +0.12
    0.03
    762
    +0.10
    0.03
    172
    +0.10
    0.02
    Negative Logits
    Offline
    -0.78
    retty
    -0.76
    origin
    -0.69
    itars
    -0.69
    grade
    -0.66
     Quan
    -0.66
    illary
    -0.66
    iency
    -0.66
    orians
    -0.65
    stra
    -0.64
    POSITIVE LOGITS
     notice
    0.97
     laugh
    0.94
     grin
    0.90
     feel
    0.87
     overhe
    0.86
     smile
    0.84
     chuckle
    0.83
     breath
    0.80
     wonder
    0.78
     glance
    0.78
    Activations Density 0.192%

    No Known Activations