© 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. 14148
    Prev
    Next
    INDEX
    Explanations

    special characters and symbols in the text

    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
    +0.33
    2.1%
    64
    +0.27
    1.7%
    156
    +0.17
    1.1%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    64
    +0.33
    0.20
    271
    +0.27
    0.04
    162
    +0.17
    0.04
    Negative Logits
    kered
    -1.61
    ftware
    -1.57
    arity
    -1.57
    iginally
    -1.56
    ressions
    -1.54
    unnumbered
    -1.50
    optera
    -1.47
    odge
    -1.47
    rent
    -1.47
     control
    -1.46
    POSITIVE LOGITS
    ®
    5.09
    ¡
    5.07
    ¨
    5.05
    ¸
    5.00
    «
    4.96
    ¹
    4.95
    ī
    4.93
    ¶
    4.88
    ¼
    4.86
    ½
    4.76
    Activations Density 0.335%

    No Known Activations