© 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. 25521
    Prev
    Next
    INDEX
    Explanations

    references to sports and athletic-related content

    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
    311
    +0.11
    0.6%
    227
    +0.11
    0.6%
    289
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    311
    +0.11
    0.03
    23
    +0.11
    0.01
    198
    +0.10
    0.03
    Negative Logits
    elves
    -1.87
    league
    -1.80
    nan
    -1.71
    quest
    -1.58
    lists
    -1.51
     fiction
    -1.47
     shape
    -1.47
    panic
    -1.46
     repertoire
    -1.46
     arena
    -1.45
    POSITIVE LOGITS
     button
    1.51
    ·
    1.44
     Note
    1.43
    rost
    1.41
    oxifen
    1.40
     note
    1.38
    vents
    1.37
    arton
    1.36
    ometh
    1.33
     [(
    1.33
    Activations Density 0.320%

    No Known Activations