© 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. 26116
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the reasons for actions or events

    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
    12
    +0.15
    0.8%
    474
    +0.12
    0.7%
    176
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    69
    +0.15
    0.05
    12
    +0.12
    0.02
    478
    +0.11
    0.00
    Negative Logits
    į
    -2.20
    ħ
    -2.01
    º
    -1.99
    ½
    -1.92
    Ĩ
    -1.91
    née
    -1.75
    chus
    -1.68
    ·¸
    -1.67
    ·
    -1.67
    oks
    -1.67
    POSITIVE LOGITS
     assumptions
    1.93
     treating
    1.87
     choosing
    1.85
     invoking
    1.79
     assuming
    1.65
     demands
    1.50
     mistaken
    1.49
     defaults
    1.43
     assume
    1.39
    hift
    1.39
    Activations Density 0.657%

    No Known Activations