© 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. 29976
    Prev
    Next
    INDEX
    Explanations

    instances of the word "meeting."

    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
    +0.18
    1.0%
    156
    +0.13
    0.7%
    191
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    325
    +0.18
    0.02
    305
    +0.13
    0.02
    14
    +0.11
    0.03
    Negative Logits
    ĥ½
    -1.60
    ><
    -1.60
    >&
    -1.54
     <%=
    -1.52
    ©
    -1.47
    ĸ
    -1.40
    ¦
    -1.40
    ></
    -1.40
    §
    -1.40
     COPYRIGHT
    -1.35
    POSITIVE LOGITS
    ases
    1.75
    ulates
    1.72
    atics
    1.61
    ulated
    1.61
     spacing
    1.57
    alities
    1.55
    plit
    1.52
     constraints
    1.47
    nas
    1.44
    tons
    1.43
    Activations Density 0.123%

    No Known Activations