© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 15011
    Prev
    Next
    INDEX
    Explanations

    occurrences of the term "collide"

    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
    +0.14
    0.8%
    250
    +0.10
    0.6%
    194
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    194
    +0.14
    0.01
    193
    +0.10
    0.02
    9
    +0.10
    0.01
    Negative Logits
     slightest
    -1.64
    ever
    -1.57
    ew
    -1.48
    phrine
    -1.48
    ubicin
    -1.47
     annual
    -1.46
    ria
    -1.45
    lla
    -1.45
    chell
    -1.44
     grandchildren
    -1.43
    POSITIVE LOGITS
    apses
    2.31
    oidal
    2.21
    ¼
    2.19
    ĻĤ
    2.14
    ij
    2.13
    ł
    2.12
    «
    2.11
    Ń
    2.10
    apsed
    2.06
    ateral
    2.06
    Activations Density 0.089%

    No Known Activations