© 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. 28442
    Prev
    Next
    INDEX
    Explanations

    instances of the word "tables" and its related forms

    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
    156
    +0.22
    1.2%
    81
    +0.10
    0.6%
    123
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    156
    +0.22
    0.03
    425
    +0.10
    0.03
    58
    +0.10
    0.02
    Negative Logits
    ı
    -3.44
    ³
    -3.23
    ¯
    -3.18
    -3.07
    -3.07
    -3.07
    -3.07
    <|outofrange|>
    -3.07
    ↵
    -3.07
    ↵↵
    -3.07
    POSITIVE LOGITS
    heet
    2.47
    pace
    2.45
    mith
    2.33
    ource
    2.25
    ystems
    2.19
    hell
    2.17
    chool
    2.13
    helf
    2.08
    heets
    2.04
    hots
    1.99
    Activations Density 0.176%

    No Known Activations