© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 32245
    Prev
    Next
    INDEX
    Explanations

    references to utility functions or libraries in code

    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
    392
    +0.17
    1.0%
    197
    +0.13
    0.7%
    456
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    379
    +0.17
    0.03
    79
    +0.13
    0.02
    298
    +0.12
    0.03
    Negative Logits
    ĥ
    -2.01
    away
    -1.91
     footsteps
    -1.78
    esi
    -1.75
    ctomy
    -1.69
     home
    -1.68
    up
    -1.63
     away
    -1.60
    abouts
    -1.57
    than
    -1.56
    POSITIVE LOGITS
    itarian
    1.83
    lied
    1.66
     namespace
    1.63
    rå
    1.58
    izable
    1.50
     sciences
    1.46
     sake
    1.46
    istry
    1.45
    izer
    1.43
    inary
    1.43
    Activations Density 0.306%

    No Known Activations