© 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. 24859
    Prev
    Next
    INDEX
    Explanations

    phrases related to providing additional information or details

    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
    45
    +0.11
    0.6%
    265
    +0.11
    0.6%
    288
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.11
    0.05
    390
    +0.11
    0.03
    411
    +0.11
    0.04
    Negative Logits
    ¶
    -2.12
    Ī
    -1.97
    ı
    -1.95
    į
    -1.86
    ½
    -1.85
    ļ
    -1.78
    ī
    -1.67
    ĸ
    -1.67
     vs
    -1.66
     ratio
    -1.60
    POSITIVE LOGITS
     sid
    1.63
     summar
    1.59
     ignored
    1.48
     caption
    1.46
    {'
    1.45
     advice
    1.44
     gratefully
    1.42
     welcome
    1.41
     debated
    1.41
     alerts
    1.41
    Activations Density 0.749%

    No Known Activations