© 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. 2-RES-SM
    11. 26594
    Prev
    Next
    INDEX
    Explanations

    references to individuals, particularly in discussions about statistics or outcomes related to them

    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
    123
    +0.14
    0.8%
    508
    +0.14
    0.8%
    320
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    123
    +0.14
    0.16
    204
    +0.14
    0.15
    296
    +0.13
    0.17
    Negative Logits
     Army
    -1.51
     universities
    -1.50
     Member
    -1.41
    ↵³³
    -1.39
     written
    -1.32
     admission
    -1.30
     institutions
    -1.29
     matter
    -1.24
     Navy
    -1.24
    :**
    -1.23
    POSITIVE LOGITS
    ¥
    2.15
    Ĺ
    2.13
    ľĵ
    1.94
    ĸ
    1.85
    odor
    1.84
    º
    1.79
    Į
    1.77
    Īĺ
    1.76
    Ł
    1.70
    £
    1.65
    Activations Density 5.183%

    No Known Activations