© 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. 31268
    Prev
    Next
    INDEX
    Explanations

    instances of the word "converse" and its variations, indicating a focus on conversational themes

    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
    +0.15
    0.8%
    114
    +0.13
    0.7%
    177
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.15
    0.01
    229
    +0.13
    0.01
    257
    +0.12
    0.01
    Negative Logits
    wards
    -1.47
    bris
    -1.34
    ward
    -1.32
    |$.
    -1.31
     extent
    -1.30
     probability
    -1.30
     cushion
    -1.29
    :$
    -1.28
    backs
    -1.27
    ctomy
    -1.26
    POSITIVE LOGITS
    ational
    2.21
    inely
    1.72
    itone
    1.59
    imony
    1.57
    unciation
    1.56
    ivated
    1.51
    antically
    1.50
    ión
    1.49
    ety
    1.46
    imeter
    1.44
    Activations Density 0.020%

    No Known Activations