© 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 EvalsExportsAPI 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. 10352
    Prev
    Next
    INDEX
    Explanations

    the first-person pronoun "I."

    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
    340
    +0.16
    0.9%
    156
    +0.14
    0.8%
    369
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    171
    +0.16
    0.05
    340
    +0.14
    0.06
    109
    +0.13
    0.04
    Negative Logits
    ://
    -1.94
    ionic
    -1.70
    atically
    -1.68
    standing
    -1.61
    iting
    -1.53
     masses
    -1.53
    ening
    -1.53
    fered
    -1.49
    door
    -1.45
    casting
    -1.44
    POSITIVE LOGITS
    brahim
    2.21
    Ĭ
    2.08
     Corps
    2.04
    Ĩ
    1.92
    rr
    1.89
    reland
    1.86
    ago
    1.85
    'm
    1.81
    ¾
    1.79
    ı
    1.78
    Activations Density 0.374%

    No Known Activations