© 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. 12245
    Prev
    Next
    INDEX
    Explanations

    references to pain and related conditions

    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
    156
    +0.19
    1.2%
    143
    +0.14
    0.8%
    321
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    143
    +0.19
    0.02
    394
    +0.14
    0.02
    361
    +0.12
    0.02
    Negative Logits
     hers
    -2.05
     yours
    -1.94
     vez
    -1.77
     mine
    -1.63
    ership
    -1.59
     geneal
    -1.58
    blogger
    -1.52
     trustworthy
    -1.50
     ours
    -1.48
     campus
    -1.47
    POSITIVE LOGITS
    less
    2.54
    ting
    2.18
    ful
    2.13
     inflicted
    2.06
    lessly
    2.06
     relief
    2.00
    ingly
    1.98
    ĩ
    1.91
    lessness
    1.84
    faced
    1.84
    Activations Density 0.137%

    No Known Activations