© 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. 4-RES-SM
    11. 11858
    Prev
    Next
    INDEX
    Explanations

    the word "even" in various contexts

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    78
    +0.22
    1.4%
    312
    +0.11
    0.7%
    334
    +0.09
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    312
    +0.22
    0.02
    334
    +0.11
    0.01
    241
    +0.09
    0.02
    Negative Logits
     already
    -1.40
    nae
    -1.39
    imals
    -1.30
     dataset
    -1.29
     microarray
    -1.24
     litter
    -1.17
    makers
    -1.15
     shaping
    -1.14
     anatomy
    -1.12
     wherever
    -1.11
    POSITIVE LOGITS
     slightest
    1.86
    handed
    1.50
    ÑĢем
    1.47
    Ñģли
    1.45
    sight
    1.43
    ÑĥÑĩ
    1.39
    ancial
    1.36
    minded
    1.35
    aked
    1.34
    dition
    1.31
    Activations Density 0.062%

    No Known Activations