© 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. 28207
    Prev
    Next
    INDEX
    Explanations

    terms related to intellectual property, software licensing, and associated documentation

    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
    156
    +0.18
    1.0%
    17
    +0.15
    0.9%
    509
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    148
    +0.18
    0.05
    376
    +0.15
    0.04
    30
    +0.13
    0.07
    Negative Logits
    Ļª
    -1.71
     testify
    -1.60
     dawn
    -1.60
    ĨĴ
    -1.59
    ĵ
    -1.57
    ľ
    -1.55
    ]{}
    -1.48
    ney
    -1.47
    adal
    -1.43
    Ĵ
    -1.39
    POSITIVE LOGITS
    quarters
    1.54
     PURPOSE
    1.53
     isn
    1.47
    !\
    1.47
    icture
    1.43
    00001
    1.42
    itons
    1.42
    ources
    1.41
    drawable
    1.40
    opsis
    1.39
    Activations Density 1.467%

    No Known Activations