© 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
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. MLP Post
    9. 2-MLP-SM
    11. 27036
    Prev
    Next
    INDEX
    Explanations

    references to strikes or violent actions 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
    217
    +0.18
    1.0%
    55
    +0.13
    0.7%
    78
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    217
    +0.18
    0.11
    299
    +0.13
    0.03
    410
    +0.13
    0.02
    Negative Logits
    piece
    -1.76
    pieces
    -1.62
    ality
    -1.55
    ffer
    -1.54
    market
    -1.51
     compared
    -1.51
    ifies
    -1.48
     Owner
    -1.46
    xico
    -1.44
    iat
    -1.41
    POSITIVE LOGITS
     cy
    1.64
     strict
    1.60
    cens
    1.59
    ĨĴ
    1.55
    ĻĤ
    1.52
     violet
    1.51
     thrill
    1.47
    eric
    1.43
     paran
    1.42
     solitary
    1.42
    Activations Density 2.170%

    No Known Activations