© 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. 12111
    Prev
    Next
    INDEX
    Explanations

    specific names and references related to political or economic contexts

    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
    271
    +0.13
    0.8%
    212
    +0.12
    0.7%
    203
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    501
    +0.13
    0.03
    203
    +0.12
    0.04
    410
    +0.11
    0.04
    Negative Logits
    iating
    -1.71
     Commonwealth
    -1.68
    ctors
    -1.48
     alike
    -1.47
     invention
    -1.46
    nae
    -1.44
    iginally
    -1.42
     introduction
    -1.40
    isation
    -1.39
    isations
    -1.38
    POSITIVE LOGITS
    Īĺ
    4.03
    Ľ
    3.88
    Ļ
    3.81
    ©
    3.79
    ī
    3.78
    ŀ
    3.75
    ¥
    3.72
    ł
    3.67
    ¯
    3.62
    Ł
    3.61
    Activations Density 0.306%

    No Known Activations