© 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. 2-RES-SM
    11. 11061
    Prev
    Next
    INDEX
    Explanations

    configurations related to various resource parameters in coding environments

    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
    478
    +0.15
    0.9%
    59
    +0.14
    0.8%
    165
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    165
    +0.15
    0.05
    59
    +0.14
    0.04
    37
    +0.13
    0.04
    Negative Logits
     art
    -1.70
    ingu
    -1.56
    ESULT
    -1.55
     verge
    -1.50
    ocene
    -1.50
     Sciences
    -1.47
     exist
    -1.46
     theory
    -1.44
    ology
    -1.41
     applicable
    -1.41
    POSITIVE LOGITS
    ĭ
    1.96
    ľĵ
    1.90
    ´
    1.83
    Ĥ¬
    1.77
    Ļª
    1.77
    «
    1.70
    ĻĤ
    1.67
    tsd
    1.65
     ole
    1.65
    ÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤ
    1.49
    Activations Density 0.143%

    No Known Activations