© 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 EvalsExportsinterp-engineNEWAPI 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. 31180
    Prev
    Next
    INDEX
    Explanations

    specific mineral and geological terms, particularly relating to their properties and locations

    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
    373
    +0.15
    0.7%
    316
    +0.11
    0.5%
    156
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.15
    0.06
    284
    +0.11
    0.04
    232
    +0.10
    0.05
    Negative Logits
    Downloadha
    -0.72
    ilogy
    -0.72
    rawdownloadcloneembedreportprint
    -0.72
    ensibly
    -0.71
    ~~~~
    -0.70
     dehuman
    -0.69
    ̶
    -0.67
     combatants
    -0.66
    gamer
    -0.65
    *****
    -0.64
    POSITIVE LOGITS
     âĵĺ
    1.25
     Miner
    1.24
    âĵĺ
    1.20
     peg
    1.18
     quarry
    1.12
     Mine
    1.11
     Mineral
    1.11
     deposit
    1.05
     mineral
    1.04
     locality
    0.99
    Activations Density 0.241%

    No Known Activations