© 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. 26778
    Prev
    Next
    INDEX
    Explanations

    references to specific years or dates

    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
    132
    +0.13
    0.7%
    142
    +0.13
    0.7%
    129
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    142
    +0.13
    0.02
    132
    +0.13
    0.02
    145
    +0.10
    0.01
    Negative Logits
     yesterday
    -1.72
     question
    -1.58
     gonna
    -1.55
     trace
    -1.55
     force
    -1.50
     behold
    -1.48
     hell
    -1.46
     Mozilla
    -1.46
    atus
    -1.45
     tonight
    -1.44
    POSITIVE LOGITS
    à¯į
    1.93
    àµį
    1.85
    nai
    1.83
    ા
    1.69
    ி
    1.63
    dam
    1.59
    ental
    1.54
    à±į
    1.46
    aea
    1.45
    dess
    1.45
    Activations Density 0.006%

    No Known Activations