© 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. 9556
    Prev
    Next
    INDEX
    Explanations

    specific years, particularly in a legal or historical context

    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
    +0.20
    1.3%
    271
    +0.10
    0.6%
    219
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    131
    +0.20
    0.04
    219
    +0.10
    0.04
    490
    +0.10
    0.03
    Negative Logits
    ialize
    -1.57
     today
    -1.54
    atics
    -1.44
    ctic
    -1.39
     beforehand
    -1.38
     please
    -1.34
     soon
    -1.33
    ching
    -1.31
    imize
    -1.29
     accumulated
    -1.28
    POSITIVE LOGITS
    Ŀ
    2.62
    Ľ
    2.53
    ¤
    2.51
    Ķ
    2.50
    IJ
    2.44
    ij
    2.44
    ¸
    2.44
    ²
    2.43
    µ
    2.40
    ·
    2.37
    Activations Density 0.122%

    No Known Activations