© 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. 2-MLP-SM
    11. 22665
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "in" and its variations in context

    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
    358
    +0.11
    0.6%
    165
    +0.10
    0.6%
    341
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    142
    +0.11
    0.06
    170
    +0.10
    0.04
    407
    +0.10
    0.06
    Negative Logits
    here
    -1.53
     RNA
    -1.45
    _(
    -1.41
    forth
    -1.39
    undry
    -1.38
    umber
    -1.38
    her
    -1.38
    iosis
    -1.36
    ly
    -1.34
    upon
    -1.33
    POSITIVE LOGITS
    acity
    1.91
     deaths
    1.61
     centre
    1.52
     forgiven
    1.42
     hell
    1.42
    enties
    1.41
     killings
    1.39
     west
    1.37
     suspicion
    1.35
     centres
    1.34
    Activations Density 0.484%

    No Known Activations