© 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. 25564
    Prev
    Next
    INDEX
    Explanations

    expressions of enjoyment or love for experiences and activities

    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
    98
    +0.12
    0.6%
    407
    +0.10
    0.6%
    295
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    434
    +0.12
    0.05
    225
    +0.10
    0.05
    219
    +0.10
    0.04
    Negative Logits
    ĸ
    -1.89
     ideal
    -1.46
     cool
    -1.43
     tune
    -1.37
    ivity
    -1.36
    ive
    -1.35
     amaz
    -1.35
     ultimate
    -1.35
     cold
    -1.34
     Computing
    -1.33
    POSITIVE LOGITS
    Verlag
    1.78
    riber
    1.58
    legraph
    1.58
    arynge
    1.50
     appendix
    1.48
     cited
    1.47
    vall
    1.45
    earchers
    1.43
    batim
    1.43
    VERTISEMENT
    1.37
    Activations Density 0.486%

    No Known Activations