© 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. 25610
    Prev
    Next
    INDEX
    Explanations

    the word "besides"

    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
    376
    +0.17
    0.9%
    478
    +0.12
    0.7%
    25
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    25
    +0.17
    0.01
    216
    +0.12
    0.01
    128
    +0.12
    0.01
    Negative Logits
    OPE
    -1.53
    ISE
    -1.52
    ergic
    -1.46
    izumab
    -1.46
    ISA
    -1.41
    ented
    -1.39
    &+
    -1.36
    duino
    -1.33
    rupt
    -1.31
    BS
    -1.31
    POSITIVE LOGITS
    lining
    1.63
    hang
    1.63
     successive
    1.45
    writing
    1.44
    stances
    1.44
     directions
    1.38
     insanity
    1.34
     there
    1.32
     hurry
    1.32
     deleting
    1.30
    Activations Density 0.009%

    No Known Activations