© 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. 1-RES-SM
    11. 24768
    Prev
    Next
    INDEX
    Explanations

    the phrase "of" in 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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    17
    +0.18
    1.0%
    161
    +0.16
    0.9%
    295
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    295
    +0.18
    0.06
    136
    +0.16
    -0.01
    9
    +0.13
    0.04
    Negative Logits
    berg
    -1.45
    ieux
    -1.45
    kowski
    -1.42
    feld
    -1.41
    vation
    -1.41
    ocene
    -1.39
    helf
    -1.36
     appell
    -1.35
    Aldrich
    -1.34
     erected
    -1.33
    POSITIVE LOGITS
    ľĵ
    2.65
    Ģ
    2.52
    ¥
    2.38
    µ
    2.19
     ourselves
    2.18
    Į
    2.13
    «
    2.12
    Īĺ
    2.11
     yourself
    2.03
     your
    2.02
    Activations Density 0.693%

    No Known Activations