© 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. 25550
    Prev
    Next
    INDEX
    Explanations

    symbols and punctuation marks that indicate operations or separations in text

    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
    203
    +0.16
    0.9%
    111
    +0.15
    0.8%
    25
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    430
    +0.16
    0.01
    247
    +0.15
    0.01
    94
    +0.11
    0.01
    Negative Logits
    :&
    -1.82
    ipel
    -1.60
    aste
    -1.48
    astics
    -1.46
     Association
    -1.45
    orate
    -1.44
    orect
    -1.43
    estinal
    -1.43
    (*
    -1.39
    )?
    -1.38
    POSITIVE LOGITS
    Ļª
    2.04
    ī
    2.01
    ĨĴ
    1.96
    º
    1.94
    yet
    1.77
    coated
    1.68
    grown
    1.61
    Ñħод
    1.54
    dashed
    1.50
    eyed
    1.49
    Activations Density 0.092%

    No Known Activations