© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 4-RES-SM
    6. 11629
    Prev
    Next
    INDEX
    Explanations

    terms related to variation and diversity in contexts such as social issues or demographics

    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
    21
    +0.21
    1.3%
    368
    +0.15
    0.9%
    313
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    21
    +0.21
    0.03
    9
    +0.15
    0.04
    351
    +0.12
    0.07
    Negative Logits
    ting
    -1.98
    lined
    -1.87
    tered
    -1.84
    nier
    -1.74
    ted
    -1.71
    terest
    -1.70
    TA
    -1.70
    ta
    -1.69
    tering
    -1.63
    ty
    -1.59
    POSITIVE LOGITS
    ably
    2.17
    ableness
    2.04
    ability
    1.95
    ety
    1.94
    ¡
    1.91
    eties
    1.86
    été
    1.74
    ¨
    1.67
    abil
    1.65
    Ł
    1.64
    Activations Density 0.661%

    No Known Activations