© 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. 30815
    Prev
    Next
    INDEX
    Explanations

    references to color and its various attributes

    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
    +0.20
    1.1%
    116
    +0.17
    1.0%
    113
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    116
    +0.20
    0.03
    113
    +0.17
    0.04
    269
    +0.13
    0.03
    Negative Logits
    ±
    -1.88
    ĻĤ
    -1.83
    -1.78
    -1.78
    ↵
    -1.78
    -1.78
    -1.78
    č↵
    -1.78
    <|outofrange|>
    -1.78
    ↵  âĢĥ
    -1.78
    POSITIVE LOGITS
    imetric
    2.30
    imetry
    2.02
    coat
    1.83
    picker
    1.81
    less
    1.77
    ados
    1.74
    ado
    1.74
     LEDs
    1.67
    imeter
    1.66
     badge
    1.62
    Activations Density 0.124%

    No Known Activations