© 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. 14491
    Prev
    Next
    INDEX
    Explanations

    instances of the word "now"

    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
    183
    +0.14
    0.7%
    476
    +0.12
    0.7%
    329
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    329
    +0.14
    0.05
    476
    +0.12
    0.05
    257
    +0.11
    0.04
    Negative Logits
    ĻĤ
    -6.51
    Ļª
    -5.00
    į
    -4.88
    ↵↵
    -4.86
    -4.86
                ↵
    -4.86
    <|outofrange|>
    -4.86
    ↵
    -4.86
    ↵
    -4.86
    -4.86
    POSITIVE LOGITS
    adays
    2.49
     extinct
    2.16
     officially
    1.84
     obsolete
    1.84
    here
    1.70
     Playing
    1.51
     firmly
    1.47
    rael
    1.44
     abandoned
    1.44
     underway
    1.42
    Activations Density 0.384%

    No Known Activations