© 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 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. 24990
    Prev
    Next
    INDEX
    Explanations

    phrases indicating sources or origins

    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
    281
    +0.12
    0.7%
    286
    +0.12
    0.6%
    508
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    440
    +0.12
    0.03
    356
    +0.12
    0.06
    508
    +0.12
    0.05
    Negative Logits
    poons
    -1.88
    hood
    -1.72
    ility
    -1.60
    ization
    -1.60
    ities
    -1.54
    iousness
    -1.52
    garten
    -1.50
    issance
    -1.48
    teral
    -1.47
     {#
    -1.45
    POSITIVE LOGITS
    ĥ½
    2.21
    Ł
    2.17
    ĥ
    2.17
    «
    2.12
    ŀ
    2.03
    Ĺ
    1.98
    ľĵ
    1.94
    £
    1.89
    Ń
    1.88
    ¡
    1.87
    Activations Density 0.188%

    No Known Activations