© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 23312
    Prev
    Next
    INDEX
    Explanations

    names of people or organizations associated with various contexts

    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
    23
    +0.31
    1.7%
    232
    +0.13
    0.7%
    343
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.31
    0.15
    232
    +0.13
    0.17
    125
    +0.11
    0.15
    Negative Logits
     League
    -1.72
    ului
    -1.68
     Archives
    -1.68
    enos
    -1.65
     Agency
    -1.63
    ÃŃs
    -1.61
    ág
    -1.61
     Office
    -1.59
    ŀ
    -1.59
     Database
    -1.52
    POSITIVE LOGITS
    ]{.
    1.83
    ding
    1.55
    inally
    1.55
    ollowing
    1.53
    kered
    1.50
    orously
    1.47
     "*
    1.45
    dling
    1.45
     classifying
    1.43
    rying
    1.43
    Activations Density 2.941%

    No Known Activations