© 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. 24823
    Prev
    Next
    INDEX
    Explanations

    the word "ons" in various contexts, indicating a focus on suffixes or plural forms

    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
    52
    +0.14
    0.8%
    247
    +0.13
    0.7%
    260
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    260
    +0.14
    0.03
    144
    +0.13
    0.03
    247
    +0.13
    0.03
    Negative Logits
    ĵ
    -3.97
    ĻĤ
    -3.91
    ĥ
    -3.66
    ·
    -3.62
    į
    -3.50
    »
    -3.47
    ı
    -3.46
    Ĺ
    -3.42
    ¦
    -3.37
    ±
    -3.33
    POSITIVE LOGITS
    heets
    2.47
    ource
    2.38
    heet
    2.36
    iewicz
    2.32
    pace
    2.31
    piration
    2.31
    creen
    2.10
    ortium
    2.08
    mith
    2.02
    nel
    2.02
    Activations Density 0.165%

    No Known Activations