© 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. 31384
    Prev
    Next
    INDEX
    Explanations

    references to geographic features, places, or trails

    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
    403
    +0.15
    0.8%
    98
    +0.15
    0.8%
    490
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    403
    +0.15
    0.09
    365
    +0.15
    0.09
    434
    +0.14
    0.11
    Negative Logits
    ¦
    -4.45
    Ń
    -4.44
    ļ
    -4.37
    ½
    -4.33
    ¬
    -4.32
    ³
    -4.29
    ł
    -4.23
    -4.23
    -4.23
    -4.23
    POSITIVE LOGITS
    same
    1.57
    appointed
    1.45
    '));
    1.42
    roads
    1.41
    whose
    1.31
    Copyright
    1.30
    spread
    1.30
    Category
    1.25
    $.[]{
    1.25
    Source
    1.25
    Activations Density 2.713%

    No Known Activations