© 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. 32102
    Prev
    Next
    INDEX
    Explanations

    elements associated with technical specifications or instructions

    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
    198
    +0.25
    1.5%
    17
    +0.16
    0.9%
    382
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    198
    +0.25
    0.10
    442
    +0.16
    0.10
    342
    +0.13
    0.05
    Negative Logits
    µ
    -2.54
    ¥
    -2.40
    ĭ
    -2.27
    ¸
    -2.20
    Ŀ
    -2.17
    §
    -2.15
    ¨
    -2.13
    ĥ½
    -2.13
    Ī
    -2.10
    ĥ
    -2.09
    POSITIVE LOGITS
     heels
    1.42
    enne
    1.38
     saw
    1.36
    ierno
    1.35
    cket
    1.28
    ivered
    1.26
     onwards
    1.25
     Instead
    1.23
     attenuated
    1.23
     nor
    1.22
    Activations Density 2.717%

    No Known Activations