© 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. 8-RES_POST_32K-OAI
    11. 5977
    Prev
    Next
    INDEX
    Explanations

    statements or expressions of opinion

    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
    373
    +0.14
    0.7%
    581
    +0.11
    0.5%
    676
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    274
    +0.14
    0.04
    70
    +0.11
    0.04
    544
    +0.10
    0.03
    Negative Logits
    enza
    -0.75
    ansk
    -0.70
     Shutterstock
    -0.67
    Īè
    -0.67
    ikarp
    -0.63
     livest
    -0.62
    yip
    -0.62
     backdrop
    -0.60
    Pers
    -0.59
     backdoor
    -0.58
    POSITIVE LOGITS
     confidently
    0.77
     definitively
    0.72
     MPG
    0.67
     Comfort
    0.62
    istically
    0.61
    rock
    0.60
    eless
    0.60
     enough
    0.60
     firsthand
    0.59
    id
    0.59
    Activations Density 0.210%

    No Known Activations