© 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 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. 10397
    Prev
    Next
    INDEX
    Explanations

    items and references related to clothing and fashion

    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
    +0.17
    1.0%
    309
    +0.16
    0.9%
    56
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    56
    +0.17
    0.00
    19
    +0.16
    0.05
    173
    +0.14
    0.03
    Negative Logits
    ĥ
    -3.08
    ĵ
    -2.85
    ±
    -2.85
    Īĺ
    -2.81
    Ĩ
    -2.54
    ļ
    -2.54
    Ĥ¬
    -2.48
    ī
    -2.41
    ĨĴ
    -2.40
    ©
    -2.40
    POSITIVE LOGITS
     jeans
    2.20
    nament
    2.04
    wear
    1.99
     pants
    1.97
    suits
    1.93
    shirts
    1.90
    shirt
    1.88
    icorn
    1.85
    strap
    1.83
    belt
    1.79
    Activations Density 0.698%

    No Known Activations