© 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. 30031
    Prev
    Next
    INDEX
    Explanations

    specific terms related to digital content

    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
    365
    +0.15
    0.9%
    156
    +0.12
    0.7%
    164
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    365
    +0.15
    0.02
    163
    +0.12
    0.02
    164
    +0.11
    0.03
    Negative Logits
    ĻĤ
    -3.27
    ®
    -3.17
    ¸
    -2.91
    ·
    -2.83
    IJ
    -2.76
    ¹
    -2.72
    ķ
    -2.64
    ¿
    -2.62
    ↵    
    -2.62
    ↵↵                               
    -2.62
    POSITIVE LOGITS
    ious
    2.69
    iousness
    2.31
    less
    2.16
    edly
    1.86
    ellar
    1.86
    eller
    1.81
    aret
    1.76
    ensing
    1.74
    ivated
    1.69
    iously
    1.67
    Activations Density 0.142%

    No Known Activations