© 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. 2-RES-SM
    11. 31049
    Prev
    Next
    INDEX
    Explanations

    occurrences of the letter 'u' across various 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/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
    156
    +0.15
    0.9%
    317
    +0.13
    0.7%
    397
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    201
    +0.15
    0.01
    97
    +0.13
    0.02
    436
    +0.12
    0.02
    Negative Logits
    optera
    -1.66
    peace
    -1.52
    wise
    -1.51
    fall
    -1.45
    hores
    -1.42
    matically
    -1.41
     Procedures
    -1.39
    door
    -1.31
     execution
    -1.31
    inent
    -1.30
    POSITIVE LOGITS
    Ŀ
    2.60
    IJ
    2.55
    Ĵ
    2.54
    »
    2.52
    ĺ
    2.46
    Ģ
    2.44
    ½
    2.43
    ¬
    2.35
    ®
    2.32
    Īĺ
    2.31
    Activations Density 0.068%

    No Known Activations