© 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. 28061
    Prev
    Next
    INDEX
    Explanations

    technical terms and identifiers related to programming and data structures

    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
    153
    +0.18
    1.1%
    98
    +0.16
    1.0%
    17
    +0.16
    1.0%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    17
    +0.18
    0.01
    271
    +0.16
    -0.03
    153
    +0.16
    0.07
    Negative Logits
    etic
    -1.47
    âĢŁ
    -1.36
    KY
    -1.29
    RD
    -1.25
    THER
    -1.23
     driving
    -1.23
     goodness
    -1.19
    1371
    -1.18
    /*
    -1.17
    ---
    -1.15
    POSITIVE LOGITS
    č↵
    2.25
    ↵        ↵
    2.25
    ↵
    2.25
    ↵
    2.25
    2.25
    ↵
    2.25
    <|outofrange|>
    2.25
    ↵
    2.25
    2.25
    2.25
    Activations Density 3.276%

    No Known Activations