© 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. 25515
    Prev
    Next
    INDEX
    Explanations

    references to talent

    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
    203
    +0.16
    0.9%
    110
    +0.15
    0.9%
    410
    +0.15
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    203
    +0.16
    0.02
    110
    +0.15
    0.01
    410
    +0.15
    0.02
    Negative Logits
    Īĺ
    -2.39
    Ļª
    -2.24
    Ĥ
    -1.92
    ĸ´
    -1.89
    Ĥ¬
    -1.87
    ĵ
    -1.79
    ¨
    -1.78
    ÃĥÃĤÃĥÃĤ
    -1.71
    ĥ
    -1.69
    ĨĴ
    -1.67
    POSITIVE LOGITS
    ley
    1.96
    ieu
    1.85
    iei
    1.84
    leys
    1.77
    lessness
    1.75
    vez
    1.72
    ie
    1.68
    iom
    1.68
    ente
    1.65
    wyn
    1.63
    Activations Density 0.106%

    No Known Activations