© 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. 13833
    Prev
    Next
    INDEX
    Explanations

    opening parentheses in mathematical or scientific 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
    156
    +0.23
    1.3%
    271
    +0.15
    0.8%
    337
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    219
    +0.23
    0.06
    200
    +0.15
    0.05
    407
    +0.12
    0.03
    Negative Logits
     entity
    -1.65
    izione
    -1.53
     Intent
    -1.47
     ()
    -1.46
    ¾
    -1.45
    obox
    -1.45
     minded
    -1.43
    ylvania
    -1.41
     00000000000000000000000000000000
    -1.41
     (“
    -1.39
    POSITIVE LOGITS
    although
    2.33
    see
    2.31
    typically
    2.27
    usually
    2.21
    approximately
    2.13
    though
    2.09
    sometimes
    2.05
    reviewed
    2.05
    ...)
    2.04
    ++)
    2.02
    Activations Density 0.207%

    No Known Activations