© 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. 26842
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the existence or presence of something

    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
    23
    +0.19
    1.1%
    478
    +0.17
    1.0%
    466
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.19
    0.12
    483
    +0.17
    0.08
    142
    +0.13
    0.08
    Negative Logits
    ł
    -3.40
    §
    -3.22
    ¥
    -3.20
    º
    -3.19
    ī
    -3.14
    ¢
    -3.13
    ģ
    -2.98
    ±
    -2.97
    Ļ
    -2.92
    İ
    -2.90
    POSITIVE LOGITS
    wolf
    1.88
     respective
    1.85
     commonly
    1.80
     respectively
    1.79
     typically
    1.79
     interchange
    1.77
     primarily
    1.72
     widely
    1.69
     likely
    1.69
     cousins
    1.68
    Activations Density 0.567%

    No Known Activations