© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 8842
    Prev
    Next
    INDEX
    Explanations

    numerical values and associated data representations

    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
    +0.54
    3.9%
    111
    +0.47
    3.4%
    333
    +0.11
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    156
    +0.54
    0.47
    111
    +0.47
    0.49
    271
    +0.11
    0.27
    Negative Logits
    ↵
    -4.32
    <|outofrange|>
    -4.32
    ↵
    -4.32
    <|outofrange|>
    -4.32
    <|outofrange|>
    -4.32
    <|outofrange|>
    -4.32
    ↵↵
    -4.32
    ↵
    -4.32
     ↵
    -4.32
    <|outofrange|>
    -4.32
    POSITIVE LOGITS
    ea
    1.44
    lle
    1.42
     acres
    1.35
    keV
    1.28
    aea
    1.26
    aterally
    1.25
    inois
    1.23
     us
    1.22
    gium
    1.20
    \}\
    1.20
    Activations Density 1.788%

    No Known Activations