© 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. 1-RES-SM
    11. 30118
    Prev
    Next
    INDEX
    Explanations

    terms related to biological treatments and their implications

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    335
    +0.15
    0.8%
    386
    +0.11
    0.6%
    63
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.15
    0.02
    271
    +0.11
    0.00
    156
    +0.11
    0.01
    Negative Logits
    hots
    -1.81
     teach
    -1.71
    ]>
    -1.53
    oner
    -1.50
    yla
    -1.45
    oretical
    -1.42
    PropertyGroup
    -1.42
    oming
    -1.41
     luck
    -1.40
    psy
    -1.39
    POSITIVE LOGITS
     gamma
    2.05
    γ
    1.72
     panel
    1.60
    ariate
    1.57
     Gamma
    1.55
    -,
    1.50
     immunoglobulin
    1.50
     metric
    1.49
     Dyn
    1.47
    roit
    1.47
    Activations Density 0.055%

    No Known Activations