© 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. 13529
    Prev
    Next
    INDEX
    Explanations

    phrases related to contact information and outreach

    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
    478
    +0.18
    1.0%
    302
    +0.12
    0.7%
    182
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    407
    +0.18
    0.12
    238
    +0.12
    0.11
    95
    +0.12
    0.11
    Negative Logits
    ·¸
    -2.59
    ¨
    -2.35
    ²
    -2.32
    ī
    -2.30
    ĸ
    -2.27
    ¤
    -2.19
    Ŀ
    -2.14
    ľ
    -2.13
    Ĭ
    -2.10
    ¯
    -2.10
    POSITIVE LOGITS
     www
    1.74
     http
    1.66
    ↵ ↵
    1.61
     newsletter
    1.61
    ://
    1.61
    doibase
    1.60
    googleapis
    1.60
    ../../
    1.59
    :`
    1.56
     newsletters
    1.55
    Activations Density 2.171%

    No Known Activations