© 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. 0-MLP-SM
    6. 28144
    Prev
    Next
    INDEX
    Explanations

    expressions of eagerness and enthusiasm

    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/0-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.0.hook_mlp_out
    Hook Layer
    0
    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
    156
    +0.17
    0.9%
    148
    +0.13
    0.8%
    362
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    114
    +0.17
    0.02
    253
    +0.13
    0.02
    317
    +0.13
    0.01
    Negative Logits
     altogether
    -1.44
     Beach
    -1.37
    Ox
    -1.32
    GridView
    -1.26
    blockList
    -1.24
     continent
    -1.24
     ovar
    -1.24
     gel
    -1.22
    roma
    -1.20
     andere
    -1.18
    POSITIVE LOGITS
    ĩ
    2.95
    Ĥ¬
    2.91
    Īĺ
    2.83
    µ
    2.83
    ±
    2.79
    ·
    2.79
    Ģ
    2.67
    ģ
    2.65
    ĻĤ
    2.64
    ĥ
    2.54
    Activations Density 0.032%

    No Known Activations