© 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. MLP Post
    5. 2-MLP-SM
    6. 25774
    Prev
    Next
    INDEX
    Explanations

    issues related to health care policies and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__mlp-sm_processed/2-mlp-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_mlp_out
    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
    310
    +0.11
    0.6%
    296
    +0.11
    0.6%
    407
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.11
    0.09
    296
    +0.11
    0.15
    356
    +0.11
    0.12
    Negative Logits
    cient
    -1.52
    [@
    -1.47
    .*;
    -1.35
    ^[@
    -1.34
    osed
    -1.33
     artificially
    -1.32
    thro
    -1.31
    ol
    -1.29
    \[[@
    -1.25
    ient
    -1.24
    POSITIVE LOGITS
    ignon
    1.58
    anza
    1.49
    ário
    1.45
    elson
    1.43
    biamo
    1.42
    azzo
    1.41
    ÅĽÄĩ
    1.35
     PURPOSE
    1.34
    Verlag
    1.33
    iamo
    1.33
    Activations Density 3.154%

    No Known Activations