© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 27253
    Prev
    Next
    INDEX
    Explanations

    special formatting characters or symbols used in legal documents

    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
    224
    +0.11
    0.6%
    350
    +0.10
    0.6%
    283
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    80
    +0.11
    0.03
    350
    +0.10
    0.03
    224
    +0.09
    0.03
    Negative Logits
    ractions
    -1.34
    activ
    -1.34
     Globe
    -1.33
     Briefly
    -1.33
    ingale
    -1.32
    coded
    -1.30
     dock
    -1.29
    indows
    -1.29
    alen
    -1.28
     minimized
    -1.28
    POSITIVE LOGITS
    ĥ½
    2.88
    ¾
    2.61
    İ
    2.50
    ↵
    2.30
    ↵
    2.30
    ↵
    2.30
    2.30
    ↵
    2.30
    <|outofrange|>
    2.30
    ↵↵
    2.30
    Activations Density 0.191%

    No Known Activations