© 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. 4-RES-SM
    11. 13544
    Prev
    Next
    INDEX
    Explanations

    references to raising awareness and making an impact regarding social issues

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    2
    +0.17
    1.0%
    252
    +0.13
    0.8%
    466
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2
    +0.17
    0.03
    374
    +0.13
    0.02
    252
    +0.13
    0.02
    Negative Logits
    Ĩ
    -2.88
    ©
    -2.62
    ĥ½
    -2.59
    £
    -2.38
    İ
    -2.34
    ĭ
    -2.34
    ¼
    -2.29
    º
    -2.28
    ı
    -2.25
    ÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤ
    -2.20
    POSITIVE LOGITS
     eyebrows
    3.20
     awareness
    2.77
     eyebrow
    2.36
     funds
    2.25
     suspicions
    2.03
     suspicion
    2.02
     thresholds
    2.00
     doubts
    1.99
     alarms
    1.99
     questions
    1.92
    Activations Density 0.393%

    No Known Activations