© 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. 23849
    Prev
    Next
    INDEX
    Explanations

    questions beginning with auxiliary verbs

    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
    182
    +0.13
    0.7%
    159
    +0.11
    0.6%
    412
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    267
    +0.13
    0.02
    237
    +0.11
    0.02
    211
    +0.10
    0.02
    Negative Logits
    omorphic
    -1.69
    owler
    -1.54
    imir
    -1.48
    jor
    -1.43
    odd
    -1.41
     psychologist
    -1.36
    ÃŃs
    -1.34
     eigenvalue
    -1.32
    oretic
    -1.28
     nec
    -1.28
    POSITIVE LOGITS
    haul
    1.64
    vertisement
    1.59
    alion
    1.55
    ipel
    1.49
    ighs
    1.45
     ‘
    1.45
    icals
    1.41
    itti
    1.33
     Athens
    1.27
    iting
    1.23
    Activations Density 0.054%

    No Known Activations