© 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. 28907
    Prev
    Next
    INDEX
    Explanations

    specific numeric patterns or data structures

    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
    408
    +0.14
    0.8%
    187
    +0.13
    0.8%
    458
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    408
    +0.14
    0.06
    187
    +0.13
    0.04
    458
    +0.12
    0.03
    Negative Logits
     vengeance
    -1.65
    hentic
    -1.54
     hers
    -1.52
     blame
    -1.45
     gonna
    -1.44
     ours
    -1.43
    renched
    -1.41
    laid
    -1.40
     justice
    -1.38
    quired
    -1.37
    POSITIVE LOGITS
    imeter
    1.97
    aurus
    1.81
    meter
    1.79
    imetric
    1.79
    Hz
    1.79
     amount
    1.75
    imum
    1.72
     Hz
    1.72
    aho
    1.62
    ession
    1.60
    Activations Density 0.148%

    No Known Activations