© 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. 10-RES_POST_32K-OAI
    6. 29867
    Prev
    Next
    INDEX
    Explanations

    dates and times

    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
    314
    +0.21
    0.9%
    194
    +0.10
    0.5%
    464
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    310
    +0.21
    0.06
    260
    +0.10
    0.06
    136
    +0.09
    0.05
    Negative Logits
     thous
    -0.72
     ul
    -0.66
     contempt
    -0.63
     complied
    -0.63
     incompetent
    -0.61
     depreciation
    -0.61
     metic
    -0.61
     justification
    -0.61
     elapsed
    -0.60
     sob
    -0.60
    POSITIVE LOGITS
    th
    1.32
    rd
    1.24
    nd
    1.08
    st
    0.97
    pm
    0.93
    TH
    0.86
    tra
    0.83
    kt
    0.83
    rez
    0.81
    tle
    0.81
    Activations Density 0.595%

    No Known Activations