© 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. 28671
    Prev
    Next
    INDEX
    Explanations

    specific references to detailed information or facts

    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
    365
    +0.16
    0.9%
    376
    +0.14
    0.8%
    156
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    365
    +0.16
    0.02
    288
    +0.14
    0.02
    378
    +0.11
    0.03
    Negative Logits
    §
    -3.83
    Ļª
    -3.69
    ↵
    -3.69
    ↵
    -3.69
    ↵
    -3.69
    -3.69
     ↵
    -3.69
    <|outofrange|>
    -3.69
    č↵
    -3.69
    ↵
    -3.69
    POSITIVE LOGITS
    ()[
    1.65
    č↵
    1.63
     item
    1.60
     detail
    1.54
    where
    1.46
    adapter
    1.46
     structure
    1.46
    [(
    1.44
    pieces
    1.44
    item
    1.43
    Activations Density 0.086%

    No Known Activations