© 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. 10-RES_POST_32K-OAI
    11. 29733
    Prev
    Next
    INDEX
    Explanations

    numeric data or statistical information

    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
    430
    +0.21
    1.2%
    107
    +0.17
    0.9%
    153
    +0.16
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    316
    +0.21
    0.30
    153
    +0.17
    0.31
    512
    +0.16
    0.25
    Negative Logits
     enthusi
    -0.90
     nomine
    -0.90
     metic
    -0.84
     unden
    -0.83
     princ
    -0.81
    ortunately
    -0.79
     newsp
    -0.76
     explan
    -0.75
     incap
    -0.73
     exha
    -0.72
    POSITIVE LOGITS
    224
    1.85
    318
    1.83
    230
    1.83
    429
    1.83
    219
    1.83
    469
    1.83
    423
    1.83
    327
    1.82
    225
    1.82
    324
    1.82
    Activations Density 2.261%

    No Known Activations