© 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. 1-RES-SM
    11. 26522
    Prev
    Next
    INDEX
    Explanations

    sequences of code or programming language syntax

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    +0.27
    1.6%
    93
    +0.13
    0.8%
    351
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    423
    +0.27
    0.05
    369
    +0.13
    0.04
    93
    +0.12
    0.05
    Negative Logits
    istration
    -2.03
    ction
    -1.61
    terday
    -1.61
    odend
    -1.58
    wolf
    -1.53
    heres
    -1.49
    ption
    -1.48
    ypse
    -1.47
    havior
    -1.46
    hpp
    -1.43
    POSITIVE LOGITS
    weet
    1.76
    ”—
    1.55
    aurus
    1.52
    ITLE
    1.52
    ween
    1.51
    urb
    1.51
    ract
    1.50
    rivial
    1.49
    resse
    1.49
    oga
    1.47
    Activations Density 0.122%

    No Known Activations