© 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
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. MLP Post
    9. 0-MLP-SM
    11. 26325
    Prev
    Next
    INDEX
    Explanations

    references to honey and its various uses

    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
    466
    +0.13
    0.7%
    369
    +0.13
    0.7%
    280
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    40
    +0.13
    0.02
    466
    +0.13
    0.01
    280
    +0.12
    0.01
    Negative Logits
    hes
    -2.05
     uterine
    -1.64
     ureth
    -1.49
     supra
    -1.47
     planned
    -1.43
     longitudinal
    -1.42
    TRODUCTION
    -1.42
     mammary
    -1.40
     heading
    -1.39
     elevation
    -1.38
    POSITIVE LOGITS
    bill
    1.86
    grass
    1.82
    casters
    1.73
    apple
    1.69
    pot
    1.67
    asek
    1.65
    writer
    1.62
    caster
    1.61
    icans
    1.56
    birds
    1.55
    Activations Density 2.255%

    No Known Activations