© 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
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 4-RES-SM
    11. 12089
    Prev
    Next
    INDEX
    Explanations

    programming constructs and syntax related to imports and component initialization

    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
    306
    +0.19
    1.1%
    307
    +0.18
    1.0%
    504
    +0.16
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    37
    +0.19
    0.00
    504
    +0.18
    0.01
    172
    +0.16
    0.03
    Negative Logits
     malnutrition
    -1.51
    orph
    -1.46
     respectively
    -1.44
    chitz
    -1.40
     signs
    -1.40
    \];
    -1.39
     thereafter
    -1.37
     ethic
    -1.34
    omycin
    -1.33
     prevailed
    -1.33
    POSITIVE LOGITS
    ¾
    3.17
    ¿
    3.01
    ±
    2.99
    ·
    2.88
    Ĺ
    2.86
    ³
    2.86
    §
    2.81
    ļ
    2.77
    °
    2.74
    ij
    2.74
    Activations Density 0.127%

    No Known Activations