© 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. 30721
    Prev
    Next
    INDEX
    Explanations

    terms related to roots in various contexts

    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
    260
    +0.13
    0.7%
    364
    +0.11
    0.6%
    59
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    260
    +0.13
    0.02
    364
    +0.11
    0.02
    57
    +0.10
    0.02
    Negative Logits
    ellow
    -1.75
    HECK
    -1.44
    ributes
    -1.35
    quire
    -1.35
    olate
    -1.34
    ibaba
    -1.33
    '));
    -1.33
    Broad
    -1.32
    amily
    -1.30
    '))
    -1.30
    POSITIVE LOGITS
    hart
    1.72
     sect
    1.64
    kit
    1.63
    ”,
    1.60
    doms
    1.50
    imony
    1.48
    etable
    1.46
     canals
    1.45
    !”
    1.43
     behind
    1.43
    Activations Density 0.416%

    No Known Activations