© 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. 31244
    Prev
    Next
    INDEX
    Explanations

    programming-related terms 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/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
    312
    +0.15
    0.9%
    222
    +0.13
    0.7%
    491
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    312
    +0.15
    0.05
    74
    +0.13
    0.03
    222
    +0.12
    0.03
    Negative Logits
     Plaintiff
    -1.63
     Virgin
    -1.53
     dealership
    -1.39
     PCa
    -1.38
    InstanceState
    -1.37
     consequence
    -1.35
     Tennessee
    -1.34
     EA
    -1.34
     probable
    -1.32
     interstate
    -1.32
    POSITIVE LOGITS
     -*-
    2.01
    {}{
    1.61
    ascii
    1.57
    ähler
    1.55
    ticos
    1.54
    Ñİ
    1.54
    otyping
    1.52
    anish
    1.50
    otyped
    1.47
    roup
    1.46
    Activations Density 0.412%

    No Known Activations