© 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. 30777
    Prev
    Next
    INDEX
    Explanations

    instances of the word "pec."

    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
    241
    +0.14
    0.8%
    108
    +0.12
    0.7%
    217
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    366
    +0.14
    0.01
    41
    +0.12
    0.01
    454
    +0.11
    0.01
    Negative Logits
    ´
    -2.94
    ĩ
    -2.31
    µ
    -2.29
    ľ
    -2.24
    Ļ
    -2.22
    Ĥ¬
    -2.19
    ĸ´
    -2.15
    ·¸
    -2.15
    §
    -2.12
    ¿
    -2.11
    POSITIVE LOGITS
    ifically
    1.83
     awards
    1.82
    posium
    1.67
     Awards
    1.66
    lege
    1.65
    finder
    1.65
    arium
    1.63
    nership
    1.61
    ifications
    1.60
     Award
    1.59
    Activations Density 1.019%

    No Known Activations