© 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. 27023
    Prev
    Next
    INDEX
    Explanations

    references to software components or developer-related terminology

    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
    127
    +0.12
    0.6%
    290
    +0.11
    0.6%
    330
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    424
    +0.12
    0.03
    37
    +0.11
    0.05
    127
    +0.11
    0.11
    Negative Logits
    '">
    -1.42
    Collections
    -1.37
    Table
    -1.36
    Wrapper
    -1.32
    Based
    -1.31
    Additional
    -1.30
    Inflater
    -1.29
    provided
    -1.29
     trusted
    -1.28
    INCLUDING
    -1.26
    POSITIVE LOGITS
     yourselves
    1.78
     yourself
    1.70
    §
    1.66
     oneself
    1.57
    tering
    1.56
    eness
    1.55
    ¾
    1.54
    ļ
    1.48
    ĥ½
    1.46
    ensen
    1.45
    Activations Density 1.983%

    No Known Activations