© 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. 30411
    Prev
    Next
    INDEX
    Explanations

    plural nouns related to people or roles

    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
    144
    +0.14
    0.8%
    459
    +0.14
    0.8%
    73
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    73
    +0.14
    0.04
    459
    +0.14
    0.05
    144
    +0.13
    0.03
    Negative Logits
    ¿½
    -3.11
    ı
    -3.11
    ĥ½
    -3.08
    ©
    -2.85
    -2.79
    ↵↵
    -2.79
    ↵
    -2.79
    -2.79
            ↵
    -2.79
    ↵↵
    -2.79
    POSITIVE LOGITS
    pace
    2.32
    ue
    1.94
    pective
    1.92
    clerosis
    1.90
    orbent
    1.85
    iew
    1.81
    enthal
    1.77
    pread
    1.76
    hops
    1.73
    perse
    1.68
    Activations Density 0.249%

    No Known Activations