© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 25659
    Prev
    Next
    INDEX
    Explanations

    references to positions in American football, specifically wide receivers and quarterbacks

    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
    410
    +0.13
    0.7%
    256
    +0.11
    0.6%
    66
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    161
    +0.13
    0.01
    0
    +0.11
    0.01
    225
    +0.10
    0.01
    Negative Logits
     descent
    -1.63
    rifug
    -1.60
    aneously
    -1.60
    irmed
    -1.58
    ctica
    -1.55
    ypse
    -1.52
    ↵		 
    -1.52
    abine
    -1.52
    cibly
    -1.50
    thood
    -1.50
    POSITIVE LOGITS
    olver
    1.52
    ings
    1.50
    matter
    1.49
    mith
    1.47
     calculus
    1.44
    inger
    1.42
    olve
    1.40
     refers
    1.39
    posed
    1.37
    ONG
    1.35
    Activations Density 1.549%

    No Known Activations