© 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. 9546
    Prev
    Next
    INDEX
    Explanations

    specific essay topics or related content in written works

    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
    25
    +0.32
    2.3%
    156
    +0.31
    2.2%
    111
    +0.30
    2.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.32
    0.55
    156
    +0.31
    0.41
    510
    +0.30
    0.32
    Negative Logits
    -7.11
    <|outofrange|>
    -7.11
    ↵
    -7.11
    ↵↵
    -7.11
    č↵
    -7.11
    ↵
    -7.11
    ↵↵
    -7.11
    ↵↵
    -7.11
    ↵↵
    -7.11
    <|outofrange|>
    -7.11
    POSITIVE LOGITS
    olia
    1.41
    uin
    1.38
    ourage
    1.38
    ment
    1.37
    thems
    1.34
    mentation
    1.33
    не
    1.27
    ardo
    1.27
    het
    1.27
    his
    1.26
    Activations Density 1.788%

    No Known Activations