© 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. 4-RES-SM
    11. 14754
    Prev
    Next
    INDEX
    Explanations

    programming constructs and functional elements in code

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    21
    +0.25
    1.5%
    156
    +0.23
    1.4%
    397
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    156
    +0.25
    0.05
    111
    +0.23
    0.04
    199
    +0.13
    0.03
    Negative Logits
    ↵
    -3.17
    ↵↵
    -3.17
    č↵
    -3.17
    -3.17
    <|outofrange|>
    -3.17
    -3.17
    <|outofrange|>
    -3.17
    ↵
    -3.17
    ↵  ³³³
    -3.17
    č↵
    -3.17
    POSITIVE LOGITS
     my
    2.53
     myself
    2.12
     My
    1.87
     I
    1.65
     $('#
    1.59
     $("#
    1.54
     sql
    1.54
     me
    1.53
    My
    1.47
     Sql
    1.45
    Activations Density 0.137%

    No Known Activations