© 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. 26703
    Prev
    Next
    INDEX
    Explanations

    mentions of agents and their roles

    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
    111
    +0.12
    0.6%
    267
    +0.12
    0.6%
    411
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    410
    +0.12
    0.02
    162
    +0.12
    0.03
    23
    +0.11
    0.01
    Negative Logits
    itsu
    -1.73
    esta
    -1.47
    =(
    -1.46
    anking
    -1.43
    ost
    -1.43
    oids
    -1.42
    aque
    -1.40
    ielder
    -1.40
    anged
    -1.39
    ero
    -1.39
    POSITIVE LOGITS
     Parenthood
    1.67
     Leah
    1.58
    reland
    1.57
     admit
    1.55
    aukee
    1.54
     husbands
    1.51
    ships
    1.50
     Lincoln
    1.47
     unemploy
    1.47
     Daddy
    1.44
    Activations Density 0.211%

    No Known Activations