© 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. 25034
    Prev
    Next
    INDEX
    Explanations

    phrases indicating limits or ranges, especially those associated with "up to" and numeric values

    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
    478
    +0.14
    0.8%
    69
    +0.12
    0.7%
    213
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    69
    +0.14
    0.05
    213
    +0.12
    0.03
    432
    +0.12
    0.04
    Negative Logits
    ĸ
    -1.79
    ismus
    -1.78
    Ĭ
    -1.70
    ĺ
    -1.68
    ¥
    -1.66
    ĻĤ
    -1.65
    ensen
    -1.63
    ĭ
    -1.62
    Ļª
    -1.61
    ¾
    -1.55
    POSITIVE LOGITS
    dule
    1.55
    xygen
    1.53
    ahoma
    1.53
    vant
    1.49
    rowser
    1.48
    evo
    1.48
    ope
    1.46
    wed
    1.42
    renew
    1.41
     edition
    1.40
    Activations Density 0.332%

    No Known Activations