© 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. 28047
    Prev
    Next
    INDEX
    Explanations

    phrases indicating acceptance or rejection

    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
    202
    +0.16
    0.9%
    4
    +0.12
    0.7%
    498
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    202
    +0.16
    0.10
    253
    +0.12
    0.07
    498
    +0.11
    0.09
    Negative Logits
    quartile
    -1.43
    url
    -1.41
     census
    -1.40
     ante
    -1.40
     anonymous
    -1.39
    operated
    -1.38
    ipher
    -1.33
    ijn
    -1.32
    ncbi
    -1.30
    watson
    -1.29
    POSITIVE LOGITS
    ABLE
    2.06
    MENTS
    2.06
    ING
    1.94
    TON
    1.85
    ISTER
    1.82
     THE
    1.73
    ITION
    1.73
    MENT
    1.72
    ISTS
    1.69
    RUPT
    1.68
    Activations Density 1.341%

    No Known Activations