© 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. 4-RES-SM
    11. 12630
    Prev
    Next
    INDEX
    Explanations

    references to popular culture and media

    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
    156
    +0.60
    4.7%
    111
    +0.39
    3.0%
    25
    +0.17
    1.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    205
    +0.60
    0.48
    40
    +0.39
    0.47
    156
    +0.17
    0.40
    Negative Logits
    ĥ½
    -6.01
    ī
    -5.67
    ↵
    -5.59
    <|outofrange|>
    -5.59
    č↵
    -5.59
    ↵↵
    -5.59
    ↵↵
    -5.59
    <|outofrange|>
    -5.59
    č↵
    -5.59
    -5.59
    POSITIVE LOGITS
     alone
    1.43
    ibrary
    1.32
    olia
    1.31
    ium
    1.22
    olis
    1.22
    mology
    1.22
    ola
    1.21
    mers
    1.21
    cles
    1.21
    anga
    1.20
    Activations Density 1.228%

    No Known Activations