© 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. 2-RES-SM
    11. 26394
    Prev
    Next
    INDEX
    Explanations

    references to heroes and heroism, often in the context of adventure and bravery

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    +0.15
    0.9%
    326
    +0.14
    0.8%
    232
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    177
    +0.15
    0.04
    446
    +0.14
    0.03
    232
    +0.14
    0.06
    Negative Logits
    undry
    -1.66
    arner
    -1.58
    dz
    -1.50
    CSI
    -1.37
    owned
    -1.36
    ublic
    -1.36
    hores
    -1.34
    body
    -1.33
    rivate
    -1.33
    bys
    -1.33
    POSITIVE LOGITS
    ¨
    3.69
    §
    3.64
    ¦
    3.53
    Ł
    3.49
    Ĭ
    3.40
    ¾
    3.27
    Ĩ
    3.19
    ²
    3.19
    ł
    3.18
    ®
    3.14
    Activations Density 0.554%

    No Known Activations