© 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. 26560
    Prev
    Next
    INDEX
    Explanations

    mentions and discussions of recipes

    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
    +0.21
    1.2%
    376
    +0.13
    0.7%
    397
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    397
    +0.21
    0.02
    497
    +0.13
    0.02
    132
    +0.11
    0.02
    Negative Logits
    rapy
    -1.74
     whole
    -1.74
     fellow
    -1.73
     entire
    -1.52
     colleague
    -1.52
    ureus
    -1.48
     others
    -1.46
    IGHT
    -1.44
    TRODUCTION
    -1.44
    UST
    -1.44
    POSITIVE LOGITS
    rowave
    1.66
    fruit
    1.45
    emaker
    1.44
    fork
    1.41
    gia
    1.38
    cards
    1.36
    ivable
    1.34
    ificial
    1.34
    bol
    1.34
    ivated
    1.33
    Activations Density 0.016%

    No Known Activations