© 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 EvalsExportsinterp-engineNEWAPI 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. 26546
    Prev
    Next
    INDEX
    Explanations

    code-related constructs and operations, particularly focusing on function definitions and variable manipulations

    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
    320
    +0.21
    1.3%
    31
    +0.19
    1.1%
    326
    +0.17
    1.0%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.21
    0.21
    156
    +0.19
    0.23
    71
    +0.17
    0.23
    Negative Logits
     Lastly
    -1.43
    Fig
    -1.43
     side
    -1.38
    mentioned
    -1.38
    Figure
    -1.34
     wraps
    -1.33
     Side
    -1.28
     sleeve
    -1.28
     neighbour
    -1.26
     lid
    -1.25
    POSITIVE LOGITS
    sis
    1.52
    economic
    1.51
    starter
    1.51
    atism
    1.45
    orphism
    1.42
    \(
    1.42
    alia
    1.42
    failure
    1.40
    edes
    1.39
     purposes
    1.36
    Activations Density 4.984%

    No Known Activations