© 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. 25031
    Prev
    Next
    INDEX
    Explanations

    instances of the article "a" and other numerical qualifiers

    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
    355
    +0.14
    0.8%
    434
    +0.12
    0.7%
    48
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    436
    +0.14
    0.08
    362
    +0.12
    0.07
    72
    +0.12
    0.06
    Negative Logits
    ocs
    -1.59
     quo
    -1.46
    apid
    -1.43
    soever
    -1.39
     cages
    -1.39
    Errno
    -1.37
     limits
    -1.36
    conditions
    -1.32
    guards
    -1.30
    applied
    -1.30
    POSITIVE LOGITS
     sale
    1.74
    Ĭ
    1.72
    hire
    1.60
    arte
    1.55
    sten
    1.48
     hire
    1.46
     Wales
    1.45
    ĸ´
    1.44
    chten
    1.43
    ·¸
    1.42
    Activations Density 0.675%

    No Known Activations