© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 11739
    Prev
    Next
    INDEX
    Explanations

    technical jargon or specific coding terminology

    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
    111
    +0.65
    5.2%
    156
    +0.36
    2.9%
    271
    +0.16
    1.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.65
    0.34
    156
    +0.36
    0.23
    71
    +0.16
    0.24
    Negative Logits
    ¿
    -3.83
    ½
    -3.82
    ±
    -3.71
    ↵
    -3.61
                ↵
    -3.61
    ↵↵
    -3.61
    č↵
    -3.61
     ↵
    -3.61
     ↵
    -3.61
    <|outofrange|>
    -3.61
    POSITIVE LOGITS
     dependence
    1.23
    othermal
    1.19
    rosis
    1.19
     collisions
    1.16
     concentration
    1.15
    isance
    1.15
    amento
    1.12
    ison
    1.11
    roscopic
    1.10
    aporation
    1.10
    Activations Density 0.194%

    No Known Activations