© 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. 28289
    Prev
    Next
    INDEX
    Explanations

    references to young individuals or youth-related themes

    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
    362
    +0.16
    0.9%
    457
    +0.14
    0.8%
    156
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    487
    +0.16
    0.04
    51
    +0.14
    0.03
    362
    +0.14
    0.04
    Negative Logits
    oof
    -1.57
    ió
    -1.44
     such
    -1.38
    onte
    -1.32
    such
    -1.29
    pard
    -1.25
    pless
    -1.24
     Said
    -1.24
    aded
    -1.23
    illance
    -1.21
    POSITIVE LOGITS
     enough
    1.96
    stown
    1.94
    sters
    1.81
    stance
    1.79
    ł
    1.69
    het
    1.67
    erals
    1.67
     minds
    1.57
     adulthood
    1.56
     (\<
    1.54
    Activations Density 0.034%

    No Known Activations