© 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. 27603
    Prev
    Next
    INDEX
    Explanations

    complex structures and relations in data contexts

    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
    419
    +0.20
    1.1%
    507
    +0.15
    0.9%
    312
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    71
    +0.20
    0.21
    111
    +0.15
    0.18
    156
    +0.13
    0.20
    Negative Logits
    Ĺ
    -2.70
    Ĥ¬
    -2.63
    ±
    -2.59
    ij
    -2.57
    ª
    -2.56
    ĸ´
    -2.55
    ¾
    -2.52
    ¥
    -2.52
    ¯
    -2.51
    ĥ½
    -2.50
    POSITIVE LOGITS
     slavery
    1.44
    tering
    1.42
    etics
    1.39
    àµį
    1.39
     brewing
    1.31
     affairs
    1.31
    steine
    1.31
    ANOVA
    1.30
     publishing
    1.29
    tern
    1.27
    Activations Density 3.860%

    No Known Activations