© 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. 23718
    Prev
    Next
    INDEX
    Explanations

    chemical compounds and their interactions

    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
    253
    +0.19
    1.0%
    365
    +0.16
    0.9%
    369
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    253
    +0.19
    0.02
    452
    +0.16
    0.01
    414
    +0.12
    0.01
    Negative Logits
    amento
    -1.70
    acity
    -1.56
    aceae
    -1.53
    иÑĤел
    -1.52
    екÑĤ
    -1.51
     circumstances
    -1.50
    membrane
    -1.49
     prescription
    -1.48
     Ampl
    -1.43
    TRODUCTION
    -1.40
    POSITIVE LOGITS
    İ
    2.00
    ¾
    1.97
    ½
    1.91
    °
    1.90
    ¡
    1.87
    ĺ
    1.80
    ©
    1.80
    ±
    1.78
    ª
    1.78
    ģ
    1.77
    Activations Density 0.168%

    No Known Activations