© 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. 0-MLP-SM
    11. 29575
    Prev
    Next
    INDEX
    Explanations

    references to sales figures or metrics

    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
    156
    +0.20
    1.2%
    192
    +0.12
    0.7%
    429
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    70
    +0.20
    0.01
    429
    +0.12
    0.01
    184
    +0.12
    0.01
    Negative Logits
    woke
    -1.79
     maternal
    -1.73
     saline
    -1.70
     pregnant
    -1.66
     sperm
    -1.60
    EVER
    -1.57
    thood
    -1.53
     its
    -1.51
     yours
    -1.50
     peritoneal
    -1.47
    POSITIVE LOGITS
    ian
    2.24
    manship
    2.08
    cript
    2.06
    force
    1.93
    mith
    1.87
    iu
    1.85
    ius
    1.84
    heet
    1.78
    iano
    1.76
    uet
    1.75
    Activations Density 0.016%

    No Known Activations