© 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. 24943
    Prev
    Next
    INDEX
    Explanations

    the word "also" 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/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
    23
    +0.19
    1.1%
    318
    +0.12
    0.7%
    478
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    318
    +0.19
    0.06
    78
    +0.12
    0.06
    242
    +0.12
    0.06
    Negative Logits
    Ģ
    -2.55
    leys
    -1.89
    ¬
    -1.89
    ħ
    -1.75
    Ħ
    -1.71
    ģ
    -1.71
    Ŀ
    -1.62
    unda
    -1.62
    ade
    -1.61
    ½
    -1.59
    POSITIVE LOGITS
    seud
    1.37
    Reuters
    1.35
     Shin
    1.26
     Spacewatch
    1.24
    isenberg
    1.24
     PCT
    1.23
     Sett
    1.22
    arily
    1.21
     Emirates
    1.21
    fected
    1.20
    Activations Density 0.119%

    No Known Activations