© 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. 29666
    Prev
    Next
    INDEX
    Explanations

    the word "who."

    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
    387
    +0.13
    0.7%
    261
    +0.12
    0.7%
    32
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    206
    +0.13
    0.12
    65
    +0.12
    0.12
    106
    +0.12
    0.10
    Negative Logits
    posted
    -1.64
    istor
    -1.52
     batting
    -1.48
     fringe
    -1.43
     counted
    -1.39
     gloss
    -1.35
    cyclopedia
    -1.33
     tucked
    -1.30
    eless
    -1.30
     scrutin
    -1.28
    POSITIVE LOGITS
    ês
    1.61
    ttp
    1.57
    rapeut
    1.54
    zos
    1.53
     Edition
    1.50
    ovo
    1.46
    erate
    1.43
    ilib
    1.42
    !(
    1.42
     seas
    1.40
    Activations Density 0.110%

    No Known Activations