© 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. 28780
    Prev
    Next
    INDEX
    Explanations

    references to legal jurisdictions and court systems

    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
    271
    +0.21
    1.2%
    71
    +0.18
    1.0%
    111
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    71
    +0.21
    0.06
    271
    +0.18
    0.01
    182
    +0.14
    0.03
    Negative Logits
    Figure
    -1.61
     generation
    -1.56
     respectively
    -1.53
    ”.
    -1.52
    ”,
    -1.52
    .“
    -1.52
     etc
    -1.50
    age
    -1.49
    âĢ¦”
    -1.48
    ming
    -1.48
    POSITIVE LOGITS
    ĻĤ
    3.34
    Ļª
    3.11
    »¿
    2.65
    ĥ½
    2.49
    2.48
     ↵
    2.48
    č↵č↵
    2.48
    <|outofrange|>
    2.48
    ↵↵
    2.48
    ↵
    2.48
    Activations Density 0.202%

    No Known Activations