© 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
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 2-RES-SM
    6. 28123
    Prev
    Next
    INDEX
    Explanations

    references to biblical texts and figures

    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
    369
    +0.21
    1.2%
    156
    +0.19
    1.1%
    177
    +0.18
    1.0%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    410
    +0.21
    0.08
    177
    +0.19
    0.05
    369
    +0.18
    0.03
    Negative Logits
    ating
    -1.44
    overs
    -1.44
    ¿½
    -1.41
    ising
    -1.41
    ffic
    -1.39
    TRODUCTION
    -1.37
    isers
    -1.37
    els
    -1.36
    assing
    -1.35
     membership
    -1.32
    POSITIVE LOGITS
     aloud
    1.71
    awi
    1.67
    kowski
    1.63
    usalem
    1.61
     Snyder
    1.57
    uca
    1.55
    shaw
    1.52
    son
    1.52
     Jerem
    1.50
     HashMap
    1.42
    Activations Density 0.501%

    No Known Activations