© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 0-MLP-SM
    6. 28143
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "By"

    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
    376
    +0.21
    1.2%
    478
    +0.16
    0.9%
    46
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    208
    +0.21
    0.03
    46
    +0.16
    0.03
    280
    +0.12
    0.03
    Negative Logits
    OUP
    -1.67
    heimer
    -1.66
    ours
    -1.64
     served
    -1.63
    IR
    -1.53
    late
    -1.47
    amyl
    -1.46
    uten
    -1.39
     nowhere
    -1.35
    ind
    -1.31
    POSITIVE LOGITS
    Īĺ
    1.90
    «
    1.84
    ĨĴ
    1.82
    ¬
    1.73
    ¿
    1.72
    stand
    1.70
     means
    1.68
     otra
    1.63
     default
    1.61
    °
    1.57
    Activations Density 0.350%

    No Known Activations