© 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. 13528
    Prev
    Next
    INDEX
    Explanations

    structured programming constructs and 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/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
    413
    +0.12
    0.7%
    16
    +0.12
    0.7%
    261
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    67
    +0.12
    0.00
    261
    +0.12
    0.03
    16
    +0.11
    0.02
    Negative Logits
    áĢº
    -1.37
     Tak
    -1.32
    ·
    -1.31
    ede
    -1.30
    ¹
    -1.30
    Tak
    -1.28
    rows
    -1.27
    14514500
    -1.23
    eters
    -1.22
    ¤
    -1.21
    POSITIVE LOGITS
     L
    4.40
    L
    3.59
     l
    3.19
     lua
    2.88
     LR
    2.83
     LL
    2.81
     LS
    2.75
     LM
    2.71
    LR
    2.69
     LA
    2.69
    Activations Density 1.424%

    No Known Activations