© 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. 2-RES-SM
    11. 28080
    Prev
    Next
    INDEX
    Explanations

    HTML table elements and their attributes

    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
    312
    +0.16
    0.9%
    83
    +0.14
    0.8%
    407
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    312
    +0.16
    0.13
    182
    +0.14
    0.13
    268
    +0.12
    0.11
    Negative Logits
    ĻĤ
    -2.63
    ĨĴ
    -2.24
    ª
    -2.23
    <|outofrange|>
    -2.19
    ↵        ↵
    -2.19
    ↵
    -2.19
    <|outofrange|>
    -2.19
    -2.19
    ↵
    -2.19
    ↵
    -2.19
    POSITIVE LOGITS
    openh
    1.45
    aping
    1.44
    aring
    1.42
    ging
    1.42
     respects
    1.35
     achievable
    1.34
    orems
    1.30
    arean
    1.30
    cribing
    1.28
    mpt
    1.28
    Activations Density 4.399%

    No Known Activations