© 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. 30992
    Prev
    Next
    INDEX
    Explanations

    phrases or contexts indicating opposition or resistance

    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
    478
    +0.14
    0.8%
    186
    +0.14
    0.7%
    69
    +0.14
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    69
    +0.14
    0.04
    282
    +0.14
    0.03
    506
    +0.14
    0.03
    Negative Logits
     referred
    -1.79
    ian
    -1.73
    aration
    -1.54
     called
    -1.53
    ary
    -1.50
    ication
    -1.47
     Broadcasting
    -1.42
    OST
    -1.41
     advised
    -1.37
     Parish
    -1.36
    POSITIVE LOGITS
    Ĥ¬
    2.48
    ¶
    2.42
    ½
    2.30
    2.29
    2.29
    <|outofrange|>
    2.29
    2.29
    ↵
    2.29
    ↵
    2.29
    ↵
    2.29
    Activations Density 0.213%

    No Known Activations