© 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
    2. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Residual Post - 32k
    5. 8-RES_POST_32K-OAI
    6. 6000
    Prev
    Next
    INDEX
    Explanations

    instances of the word "same."

    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
    408
    +0.14
    0.6%
    213
    +0.10
    0.5%
    358
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    162
    +0.14
    0.06
    408
    +0.10
    0.05
    423
    +0.09
    0.05
    Negative Logits
    *=-
    -0.91
    skirts
    -0.81
    twitch
    -0.76
    ãĥ¼ãĤ¯
    -0.74
    irtual
    -0.71
    Äĩ
    -0.69
    uckle
    -0.69
     Khe
    -0.67
    âĵĺ
    -0.67
    anism
    -0.66
    POSITIVE LOGITS
     thing
    1.27
     amount
    1.17
     sized
    1.00
     exact
    0.98
     person
    0.94
     extent
    0.89
     result
    0.88
     kind
    0.88
     object
    0.87
     number
    0.84
    Activations Density 0.093%

    No Known Activations