© 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. 25996
    Prev
    Next
    INDEX
    Explanations

    the phrase "World" and its variants in different 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
    301
    +0.15
    0.8%
    52
    +0.13
    0.7%
    14
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    301
    +0.15
    0.04
    14
    +0.13
    0.04
    52
    +0.12
    0.04
    Negative Logits
    ching
    -1.86
     certain
    -1.63
     my
    -1.59
    amide
    -1.56
    ters
    -1.55
    ection
    -1.50
    hin
    -1.48
     associated
    -1.46
    ometh
    -1.45
    ments
    -1.43
    POSITIVE LOGITS
    Īĺ
    2.85
    Ĥ¬
    2.78
    ģ
    2.75
    »
    2.72
    ↵↵
    2.69
     ↵
    2.69
    ↵
    2.69
    ↵↵
    2.69
    2.69
    <|outofrange|>
    2.69
    Activations Density 0.875%

    No Known Activations