© 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. 25404
    Prev
    Next
    INDEX
    Explanations

    instances of the word "we"

    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
    494
    +0.14
    0.8%
    29
    +0.13
    0.7%
    339
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    498
    +0.14
    0.11
    184
    +0.13
    0.10
    138
    +0.12
    0.09
    Negative Logits
     Campaign
    -1.46
    APTER
    -1.39
    wik
    -1.39
     example
    -1.35
     Appellate
    -1.35
    summary
    -1.34
    ostream
    -1.33
    NN
    -1.30
    ruz
    -1.30
    ClCompile
    -1.27
    POSITIVE LOGITS
    esis
    1.61
    arium
    1.51
    ĭ
    1.50
     its
    1.48
    ken
    1.41
    icity
    1.41
    ctomy
    1.39
    _
    1.38
    oid
    1.37
    ery
    1.35
    Activations Density 0.170%

    No Known Activations