© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 29968
    Prev
    Next
    INDEX
    Explanations

    instances of the word "doing."

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    376
    +0.17
    1.0%
    321
    +0.12
    0.7%
    148
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    158
    +0.17
    0.04
    120
    +0.12
    0.04
    486
    +0.12
    0.04
    Negative Logits
    apine
    -1.94
    noreply
    -1.82
    ieu
    -1.55
     she
    -1.53
    odia
    -1.47
    osal
    -1.44
     saying
    -1.40
    rea
    -1.38
    ément
    -1.37
    appa
    -1.36
    POSITIVE LOGITS
    xy
    1.69
     exercises
    1.67
    °
    1.63
     deficits
    1.63
     deficit
    1.60
    gs
    1.58
    gered
    1.51
    Ļ
    1.50
    ctors
    1.48
    º
    1.47
    Activations Density 0.152%

    No Known Activations