© 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. 12902
    Prev
    Next
    INDEX
    Explanations

    mentions of news networks

    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
    +0.21
    1.2%
    369
    +0.18
    1.0%
    71
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    410
    +0.21
    0.04
    443
    +0.18
    0.03
    369
    +0.14
    0.01
    Negative Logits
     threshold
    -1.66
     things
    -1.63
     quicker
    -1.58
     trypsin
    -1.58
     aged
    -1.49
     behold
    -1.46
     glyph
    -1.45
     reflux
    -1.44
     temporary
    -1.43
     certain
    -1.43
    POSITIVE LOGITS
     Broadcasting
    2.35
     Television
    2.15
     Entertainment
    1.93
     Studios
    1.88
     Productions
    1.87
     Radio
    1.86
    TV
    1.86
     Comics
    1.85
    film
    1.84
    blic
    1.82
    Activations Density 0.250%

    No Known Activations