© 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. 30981
    Prev
    Next
    INDEX
    Explanations

    the repeated use of the word "it"

    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
    400
    +0.12
    0.7%
    389
    +0.12
    0.7%
    429
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    352
    +0.12
    0.23
    185
    +0.12
    0.19
    165
    +0.11
    0.18
    Negative Logits
    axon
    -1.63
    shown
    -1.40
    unch
    -1.38
    inen
    -1.37
    amsmath
    -1.37
    FIG
    -1.33
    forcement
    -1.32
    MARK
    -1.31
    amination
    -1.31
    ady
    -1.30
    POSITIVE LOGITS
    icles
    1.71
    igos
    1.69
    ]{}]{}
    1.54
    rolet
    1.54
     winner
    1.50
    ei
    1.47
    ¨
    1.46
    arias
    1.46
    lessness
    1.45
    omonas
    1.44
    Activations Density 1.009%

    No Known Activations