© 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. 28191
    Prev
    Next
    INDEX
    Explanations

    references to virtual simulation environments and related activities

    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
    156
    +0.27
    1.7%
    369
    +0.27
    1.6%
    484
    +0.12
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    369
    +0.27
    0.10
    410
    +0.27
    0.15
    484
    +0.12
    0.10
    Negative Logits
    -2.25
    ↵
    -2.25
    -2.25
    ↵
    -2.25
     ↵
    -2.25
    ↵
    -2.25
    <|outofrange|>
    -2.25
              ↵
    -2.25
    ↵
    -2.25
    <|outofrange|>
    -2.25
    POSITIVE LOGITS
     Award
    1.56
     Coast
    1.46
    IER
    1.44
     Age
    1.42
     Corps
    1.42
    qua
    1.41
    pton
    1.40
    ilda
    1.36
     Injury
    1.36
    isan
    1.35
    Activations Density 1.119%

    No Known Activations