© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 2-RES-SM
    11. 9768
    Prev
    Next
    INDEX
    Explanations

    key topics related to the immune system and its components

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    +0.48
    3.4%
    111
    +0.44
    3.1%
    298
    +0.10
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.48
    0.18
    156
    +0.44
    0.15
    71
    +0.10
    0.15
    Negative Logits
    ↵↵
    -2.04
    ↵↵
    -2.04
     ↵
    -2.04
    -2.04
    <|outofrange|>
    -2.04
                ↵
    -2.04
     ↵
    -2.04
    <|outofrange|>
    -2.04
    <|outofrange|>
    -2.04
    ↵
    -2.04
    POSITIVE LOGITS
    /-/
    1.31
    erad
    1.30
    etitive
    1.29
     lately
    1.24
    uality
    1.23
    leneck
    1.22
    ============
    1.17
    elled
    1.13
    adays
    1.12
    tico
    1.12
    Activations Density 0.092%

    No Known Activations