© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 28730
    Prev
    Next
    INDEX
    Explanations

    references to celestial bodies, particularly the sun and moon

    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%
    420
    +0.10
    0.5%
    346
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    27
    +0.12
    0.03
    19
    +0.10
    0.03
    325
    +0.10
    0.03
    Negative Logits
     disadvant
    -0.75
     confir
    -0.75
     Flavoring
    -0.75
     Strategies
    -0.67
     Coup
    -0.65
     Cout
    -0.65
     Rural
    -0.64
     Cros
    -0.64
    ership
    -0.63
     weap
    -0.61
    POSITIVE LOGITS
    spot
    1.20
    burn
    1.17
    lit
    1.14
    pool
    1.12
    rises
    1.07
    sets
    1.04
    burning
    1.03
    flower
    1.03
    light
    0.99
    sp
    0.98
    Activations Density 0.201%

    No Known Activations