© 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. 2-MLP-SM
    11. 22897
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "the" in various contexts

    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/2-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.2.hook_mlp_out
    Hook Layer
    2
    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
    156
    +0.16
    1.0%
    406
    +0.15
    0.9%
    231
    +0.14
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    231
    +0.16
    0.10
    406
    +0.15
    0.08
    272
    +0.14
    0.09
    Negative Logits
    ]{.
    -1.77
     [$\
    -1.55
     empt
    -1.47
     dislocation
    -1.45
    INESS
    -1.44
     oxygen
    -1.43
     unfolded
    -1.42
    IDTH
    -1.40
     contrast
    -1.39
     electrons
    -1.39
    POSITIVE LOGITS
    oit
    1.81
    watson
    1.78
    amble
    1.77
    olta
    1.73
    enders
    1.71
    lei
    1.71
    ág
    1.68
    arios
    1.65
    .
    1.64
     europe
    1.61
    Activations Density 0.446%

    No Known Activations