© 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. 2-RES-SM
    11. 28530
    Prev
    Next
    INDEX
    Explanations

    significant events or milestones related to performances or productions

    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
    198
    +0.21
    1.2%
    235
    +0.14
    0.9%
    12
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    198
    +0.21
    0.08
    235
    +0.14
    0.07
    442
    +0.12
    0.07
    Negative Logits
    ¿½
    -4.71
    ¡
    -4.62
    -4.40
    -4.40
    ↵↵
    -4.40
    <|outofrange|>
    -4.40
    ↵↵
    -4.40
    -4.40
    -4.40
    ↵
    -4.40
    POSITIVE LOGITS
     seasons
    1.61
    nikov
    1.51
     Nations
    1.40
    century
    1.39
     episode
    1.38
     wars
    1.38
     times
    1.35
     exposition
    1.34
     arrives
    1.33
     epoch
    1.32
    Activations Density 1.049%

    No Known Activations