© 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. 2-RES-SM
    11. 26954
    Prev
    Next
    INDEX
    Explanations

    technical terms and coding keywords related to computer software and programming languages

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    12
    +0.13
    0.7%
    198
    +0.13
    0.7%
    231
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    184
    +0.13
    0.02
    209
    +0.13
    0.03
    230
    +0.12
    0.02
    Negative Logits
    Ĺ
    -2.08
    ?’
    -1.99
    ľĵ
    -1.94
    ’.
    -1.78
     ‘
    -1.74
    .’
    -1.72
    !’
    -1.65
    ’,
    -1.60
    Ĩ
    -1.51
    IJ
    -1.50
    POSITIVE LOGITS
    loat
    1.55
    derer
    1.42
    idegger
    1.38
     terrain
    1.33
    oreal
    1.30
    gether
    1.29
    FTWARE
    1.28
     asp
    1.28
     wiring
    1.27
     Logic
    1.27
    Activations Density 0.119%

    No Known Activations