© 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. 25146
    Prev
    Next
    INDEX
    Explanations

    references to frequency or repetition

    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
    110
    +0.12
    0.7%
    424
    +0.12
    0.7%
    500
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    424
    +0.12
    0.03
    325
    +0.12
    0.02
    110
    +0.12
    0.02
    Negative Logits
    ĥ
    -2.14
    Ħ
    -2.01
    ĸ´
    -1.93
    ĵ
    -1.85
    ¦
    -1.85
    ľĵ
    -1.83
    ©
    -1.79
    §
    -1.78
    ħ
    -1.68
    Ľ
    -1.66
    POSITIVE LOGITS
    pan
    1.90
    cale
    1.79
    eries
    1.79
     magnification
    1.77
    lot
    1.64
    chaft
    1.63
    kip
    1.62
    heets
    1.58
    heet
    1.57
     inflation
    1.54
    Activations Density 0.061%

    No Known Activations