© 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. Residuals
    9. 1-RES-SM
    11. 27225
    Prev
    Next
    INDEX
    Explanations

    code elements related to posts in a database structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__res-sm_processed/1-res-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    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
    40
    +0.14
    0.8%
    290
    +0.11
    0.6%
    295
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    40
    +0.14
    0.05
    410
    +0.11
    0.05
    17
    +0.11
    0.01
    Negative Logits
     counterpart
    -1.67
     strengths
    -1.61
     principle
    -1.58
     distinguishing
    -1.56
     <-
    -1.54
     trained
    -1.50
     advantage
    -1.50
    _."
    -1.48
     humans
    -1.46
     footprint
    -1.45
    POSITIVE LOGITS
    raine
    1.71
     mysq
    1.66
     decomp
    1.61
    irez
    1.61
     recurrence
    1.60
    php
    1.57
    iversary
    1.56
     reviews
    1.54
     rel
    1.53
    ruptcy
    1.52
    Activations Density 0.649%

    No Known Activations