© 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. 24895
    Prev
    Next
    INDEX
    Explanations

    pronouns and demonstratives

    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
    371
    +0.14
    0.8%
    421
    +0.13
    0.7%
    495
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    10
    +0.14
    0.00
    503
    +0.13
    0.00
    369
    +0.12
    0.00
    Negative Logits
    ©
    -3.67
    ¤
    -3.50
    Īĺ
    -3.42
    IJ
    -3.39
    Ł
    -3.30
    §
    -3.30
    ¥
    -3.29
    »¿
    -3.15
    ¹
    -3.11
    ¦
    -3.07
    POSITIVE LOGITS
     âĨĴ
    1.67
     »
    1.49
     clause
    1.48
    _[
    1.47
     concerned
    1.42
     (`
    1.41
    {};
    1.39
     (§
    1.37
     Palestine
    1.36
    :`
    1.36
    Activations Density 0.000%

    No Known Activations