© 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. 4-RES-SM
    11. 14400
    Prev
    Next
    INDEX
    Explanations

    phrases indicative of conditions or events that require legal consideration or action

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    466
    +0.27
    1.7%
    307
    +0.20
    1.2%
    25
    +0.14
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    466
    +0.27
    0.13
    330
    +0.20
    0.12
    459
    +0.14
    0.09
    Negative Logits
    ij
    -2.40
    ģ
    -2.30
    ¾
    -2.04
    Ļª
    -2.00
    IJ
    -2.00
    Ļ
    -1.86
    ¸
    -1.86
    ¬
    -1.85
    ĭ
    -1.85
    iste
    -1.84
    POSITIVE LOGITS
     therefore
    2.44
     hence
    2.19
     consequently
    2.16
     its
    1.91
     expects
    1.84
    therefore
    1.82
     thus
    1.82
     lacks
    1.78
     has
    1.78
     includes
    1.76
    Activations Density 0.938%

    No Known Activations