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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 29908
    Prev
    Next
    INDEX
    Explanations

    terms related to software distribution and associated limits

    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
    74
    +0.14
    0.8%
    460
    +0.11
    0.6%
    139
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    74
    +0.14
    0.02
    359
    +0.11
    0.02
    18
    +0.10
    0.01
    Negative Logits
    ľĵ
    -4.13
    Ĩ
    -4.10
    ĨĴ
    -3.98
    ĥ½
    -3.92
    ı
    -3.88
    ↵
    -3.79
    <|padding|>
    -3.79
            ↵
    -3.79
    -3.79
    -3.79
    POSITIVE LOGITS
    ystem
    1.45
    keeper
    1.40
     file
    1.39
    iant
    1.39
     files
    1.37
     entity
    1.37
    verse
    1.35
    fault
    1.35
     version
    1.35
    ystems
    1.35
    Activations Density 0.065%

    No Known Activations