© 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. 25505
    Prev
    Next
    INDEX
    Explanations

    connections regarding the implications of public actions and policies

    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
    358
    +0.14
    0.8%
    284
    +0.14
    0.8%
    206
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    284
    +0.14
    0.09
    358
    +0.14
    0.13
    193
    +0.12
    0.07
    Negative Logits
    ferroni
    -1.41
     chor
    -1.38
    il
    -1.36
    ######
    -1.33
    ting
    -1.29
     mut
    -1.29
    mut
    -1.24
     exploitation
    -1.23
    ttp
    -1.22
    ¹
    -1.22
    POSITIVE LOGITS
    zzles
    1.54
     reign
    1.53
     possessions
    1.50
    ateurs
    1.45
     Democr
    1.39
    zzle
    1.37
    isans
    1.35
    ères
    1.33
     trademarks
    1.33
    ık
    1.31
    Activations Density 4.351%

    No Known Activations