© 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. Residuals
    9. 1-RES-SM
    11. 24601
    Prev
    Next
    INDEX
    Explanations

    the word "instead."

    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
    335
    +0.12
    0.7%
    157
    +0.11
    0.6%
    165
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    335
    +0.12
    0.02
    157
    +0.11
    0.03
    15
    +0.10
    0.03
    Negative Logits
    »¿
    -2.55
    ľ
    -2.45
    §
    -2.41
    Į
    -2.36
    ģ
    -2.31
    ħ
    -2.28
    ĥ
    -2.27
    º
    -2.27
    Ĩ
    -2.21
    ¼
    -2.14
    POSITIVE LOGITS
    dated
    1.64
    ICO
    1.60
     sung
    1.54
     COUN
    1.50
    ayer
    1.39
    lund
    1.37
    imal
    1.35
     imposing
    1.34
     deduct
    1.34
    ?).
    1.33
    Activations Density 0.064%

    No Known Activations