© 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. 26369
    Prev
    Next
    INDEX
    Explanations

    key themes of significance and the repercussions of choices or actions within 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/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
    397
    +0.19
    1.1%
    240
    +0.16
    0.9%
    287
    +0.15
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    287
    +0.19
    0.18
    397
    +0.16
    0.15
    155
    +0.15
    0.13
    Negative Logits
    ĻĤ
    -3.13
    ľĵ
    -2.67
    ľ
    -2.54
    Ļª
    -2.52
    Īĺ
    -2.51
    ·¸
    -2.49
    »¿
    -2.45
    ¿
    -2.29
    soever
    -2.25
    ŀ
    -2.21
    POSITIVE LOGITS
     of
    2.39
     thereof
    2.16
     OF
    1.83
    scene
    1.63
    opot
    1.55
    ophone
    1.54
     quo
    1.49
    ceral
    1.47
     Of
    1.46
    ometric
    1.45
    Activations Density 2.086%

    No Known Activations