© 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. 29319
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Phil."

    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
    +0.12
    0.5%
    430
    +0.11
    0.5%
    213
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.12
    0.02
    374
    +0.11
    0.00
    659
    +0.10
    0.01
    Negative Logits
    CLASSIFIED
    -0.74
    FIELD
    -0.64
     Unlimited
    -0.63
    TEXTURE
    -0.63
    Reloaded
    -0.61
     Civic
    -0.58
     quo
    -0.57
     JUSTICE
    -0.57
     Aval
    -0.57
     docking
    -0.56
    POSITIVE LOGITS
    anthrop
    1.46
    adel
    1.30
    harm
    1.29
    istine
    1.27
    ando
    1.05
    andering
    1.02
    adelphia
    1.02
    omen
    0.98
    ips
    0.98
    omon
    0.93
    Activations Density 0.063%

    No Known Activations