© 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. 27574
    Prev
    Next
    INDEX
    Explanations

    references to licenses and licensing agreements

    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
    2
    +0.18
    1.0%
    490
    +0.11
    0.6%
    158
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2
    +0.18
    0.03
    42
    +0.11
    0.01
    241
    +0.10
    0.02
    Negative Logits
    ĨĴ
    -2.21
     wounded
    -1.75
    ł
    -1.75
    ij
    -1.74
    Ł
    -1.72
    ľĵ
    -1.70
    ı
    -1.69
    ĵ
    -1.63
     injured
    -1.62
    ´
    -1.62
    POSITIVE LOGITS
    bsd
    1.85
    ivo
    1.80
    ivation
    1.66
     waiver
    1.66
    LICENSE
    1.64
     eligibility
    1.63
     certificates
    1.59
    gio
    1.54
     copyrighted
    1.52
    ular
    1.52
    Activations Density 0.063%

    No Known Activations