© 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. 27972
    Prev
    Next
    INDEX
    Explanations

    references to integrated circuits and their designation

    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
    417
    +0.13
    0.8%
    177
    +0.12
    0.7%
    445
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    417
    +0.13
    0.03
    445
    +0.12
    0.02
    300
    +0.10
    0.02
    Negative Logits
    aways
    -1.82
     actual
    -1.69
     normal
    -1.63
     sudden
    -1.61
     mundane
    -1.61
    coming
    -1.61
    ../
    -1.54
     noct
    -1.50
    ../../
    -1.45
     occasional
    -1.44
    POSITIVE LOGITS
    lass
    1.80
    IENT
    1.77
    ULAR
    1.74
    ulated
    1.74
    HEP
    1.72
    ISM
    1.72
    ENS
    1.70
    LEY
    1.68
    IAL
    1.67
    IAN
    1.67
    Activations Density 0.060%

    No Known Activations