© 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. 9954
    Prev
    Next
    INDEX
    Explanations

    instances of the word "in"

    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
    307
    +0.22
    1.2%
    412
    +0.13
    0.7%
    478
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    139
    +0.22
    0.10
    166
    +0.13
    0.07
    77
    +0.12
    0.09
    Negative Logits
    Īĺ
    -2.61
    º
    -2.60
    ª
    -2.53
    ĻĤ
    -2.52
    Ń
    -2.42
    ij
    -2.38
    ²
    -2.37
    Ŀ
    -2.24
    ļ
    -2.21
    Ĺ
    -2.21
    POSITIVE LOGITS
     accordance
    2.50
     southern
    2.47
     lieu
    2.46
     order
    2.46
     downtown
    2.44
     northern
    2.34
     eastern
    2.29
    frast
    2.27
     anticipation
    2.20
     addition
    2.16
    Activations Density 0.422%

    No Known Activations