© 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 EvalsExportsAPI 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. 27352
    Prev
    Next
    INDEX
    Explanations

    file extensions, specifically those indicating text files

    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
    182
    +0.14
    0.8%
    350
    +0.12
    0.7%
    431
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    182
    +0.14
    0.02
    490
    +0.12
    0.01
    431
    +0.12
    0.01
    Negative Logits
    ·¸
    -3.14
    ´
    -2.96
    Īĺ
    -2.95
    µ
    -2.85
    ĥ
    -2.85
    Ħ
    -2.70
    Ĥ¬
    -2.66
    Ĭ
    -2.65
    Ī
    -2.60
    ÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤ
    -2.57
    POSITIVE LOGITS
    ail
    1.91
    room
    1.75
    rooms
    1.73
    orno
    1.69
    ault
    1.65
    documents
    1.63
    istry
    1.61
    aliana
    1.61
    ements
    1.60
    cfg
    1.56
    Activations Density 0.089%

    No Known Activations