© 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. 1-RES-SM
    11. 28441
    Prev
    Next
    INDEX
    Explanations

    Android-related elements and attributes within the text

    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/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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    317
    +0.12
    0.7%
    335
    +0.12
    0.6%
    384
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    384
    +0.12
    0.03
    335
    +0.12
    0.02
    317
    +0.11
    0.02
    Negative Logits
    Īĺ
    -3.93
    ĵ
    -3.84
    Ļª
    -3.67
    ĻĤ
    -3.67
    Ķ
    -3.59
    ¬
    -3.56
    ľĵ
    -3.52
    ¼
    -3.42
    ľ
    -3.41
    ĥ
    -3.37
    POSITIVE LOGITS
    atar
    1.90
    actory
    1.63
    fonts
    1.57
    dip
    1.53
    ricular
    1.48
    "}](#
    1.44
     vols
    1.43
    brush
    1.41
    à°¿
    1.39
     belt
    1.39
    Activations Density 0.057%

    No Known Activations