© 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. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. MLP Post
    9. 0-MLP-SM
    11. 29566
    Prev
    Next
    INDEX
    Explanations

    descriptions of creamy textures in food and related products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__mlp-sm_processed/0-mlp-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.0.hook_mlp_out
    Hook Layer
    0
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    156
    +0.11
    0.6%
    470
    +0.11
    0.6%
    223
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    156
    +0.11
    0.01
    408
    +0.11
    0.01
    452
    +0.11
    0.01
    Negative Logits
    orse
    -1.70
    or
    -1.70
     ¥
    -1.65
    orses
    -1.62
     row
    -1.61
    ors
    -1.54
    oral
    -1.54
    orer
    -1.51
    orian
    -1.50
    urous
    -1.49
    POSITIVE LOGITS
    »
    2.75
    Ľ
    2.70
    ¢
    2.66
    £
    2.57
    ĩ
    2.56
    ¸
    2.52
    ³
    2.50
    º
    2.46
    ·¸
    2.41
    ±
    2.41
    Activations Density 0.026%

    No Known Activations