© 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. 24818
    Prev
    Next
    INDEX
    Explanations

    patterns related to structures or systems

    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
    319
    +0.13
    0.7%
    476
    +0.12
    0.7%
    107
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    462
    +0.13
    0.01
    476
    +0.12
    0.06
    465
    +0.11
    0.07
    Negative Logits
    lights
    -1.51
    ify
    -1.49
    asts
    -1.48
    ires
    -1.45
    itted
    -1.45
    ifies
    -1.41
    ger
    -1.40
    imize
    -1.38
    okes
    -1.38
    pose
    -1.37
    POSITIVE LOGITS
     estate
    1.66
     inclusion
    1.61
     hosting
    1.57
    »¿
    1.57
    1.51
    ↵
    1.51
    1.51
    1.51
    ↵
    1.51
    ↵
    1.51
    Activations Density 1.036%

    No Known Activations