© 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
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. MLP Post
    9. 0-MLP-SM
    11. 27149
    Prev
    Next
    INDEX
    Explanations

    instances and references to trees and related terminology

    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
    +0.19
    1.1%
    132
    +0.14
    0.8%
    376
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    132
    +0.19
    0.03
    227
    +0.14
    0.02
    93
    +0.11
    0.02
    Negative Logits
    ľĵ
    -1.90
    ociation
    -1.75
    ĥ
    -1.75
    Ń
    -1.58
    ĥ½
    -1.58
    µ
    -1.50
    §
    -1.49
    ÑĢÑĭ
    -1.49
    ...'
    -1.48
    cess
    -1.48
    POSITIVE LOGITS
    ball
    2.23
    balls
    1.97
    notes
    1.77
    osaur
    1.77
    grass
    1.77
    doms
    1.72
     resembles
    1.69
    fork
    1.66
    yard
    1.63
    points
    1.58
    Activations Density 0.024%

    No Known Activations