© 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. 26251
    Prev
    Next
    INDEX
    Explanations

    the word "nothing"

    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
    +0.15
    0.8%
    165
    +0.12
    0.7%
    372
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    372
    +0.15
    0.04
    408
    +0.12
    0.04
    347
    +0.11
    0.03
    Negative Logits
    rophot
    -1.84
    estly
    -1.82
     alot
    -1.55
     countless
    -1.52
     millions
    -1.51
    ften
    -1.44
    ro
    -1.44
    rob
    -1.43
    roc
    -1.42
     many
    -1.41
    POSITIVE LOGITS
     else
    2.43
     whatsoever
    1.86
     except
    1.82
     restrictions
    1.68
     ELSE
    1.65
    stroke
    1.61
     Else
    1.58
     resembling
    1.50
    ģ
    1.47
    «
    1.47
    Activations Density 0.018%

    No Known Activations