© 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. 28411
    Prev
    Next
    INDEX
    Explanations

    mentions of document creation and authorship

    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
    422
    +0.13
    0.7%
    244
    +0.13
    0.7%
    321
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    416
    +0.13
    0.02
    103
    +0.13
    0.02
    197
    +0.12
    0.01
    Negative Logits
    Ī
    -1.71
    Ĺ
    -1.69
    ugin
    -1.66
    ."[
    -1.65
    Ľ
    -1.64
    Īĺ
    -1.63
    ?",
    -1.63
    Ł
    -1.58
    ĸ
    -1.55
    million
    -1.52
    POSITIVE LOGITS
     meantime
    1.64
     date
    1.55
    icate
    1.54
    iate
    1.54
    DateTime
    1.52
    iscuss
    1.48
    ****************************************************************************
    1.45
     agenda
    1.45
    ↵³³
    1.45
     Address
    1.44
    Activations Density 0.117%

    No Known Activations