© 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. 2-RES-SM
    11. 26962
    Prev
    Next
    INDEX
    Explanations

    various forms of the word "download."

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    +0.16
    0.9%
    339
    +0.14
    0.8%
    173
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    339
    +0.16
    0.02
    173
    +0.14
    0.01
    412
    +0.12
    0.02
    Negative Logits
    ĥ½
    -2.85
    ¹
    -2.75
    §
    -2.74
    ¯
    -2.73
    ¤
    -2.65
    Ł
    -2.65
    ·
    -2.64
    ī
    -2.63
    Ń
    -2.62
    ↵
    -2.56
    POSITIVE LOGITS
     itself
    1.93
    able
    1.91
     therefrom
    1.83
     videos
    1.75
     them
    1.69
     versions
    1.66
     transcripts
    1.61
    strap
    1.55
     footage
    1.53
     minute
    1.52
    Activations Density 0.155%

    No Known Activations