© 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
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 2-RES-SM
    6. 12403
    Prev
    Next
    INDEX
    Explanations

    programming-related terms and concepts

    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
    198
    +0.15
    0.9%
    235
    +0.15
    0.9%
    47
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    153
    +0.15
    0.05
    161
    +0.15
    0.04
    47
    +0.13
    0.16
    Negative Logits
     Photograph
    -2.02
     Tesla
    -1.54
    eks
    -1.35
    uding
    -1.34
     Nag
    -1.34
     2030
    -1.33
    APH
    -1.33
    hereinafter
    -1.28
    ridges
    -1.28
    FIG
    -1.27
    POSITIVE LOGITS
     offender
    1.57
     adversary
    1.56
     advantage
    1.41
    raints
    1.38
    nest
    1.37
    oretic
    1.37
    hip
    1.34
     proud
    1.33
    ().
    1.31
    ableness
    1.31
    Activations Density 6.123%

    No Known Activations