© 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. 28701
    Prev
    Next
    INDEX
    Explanations

    references to various forms of talent

    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
    156
    +0.18
    1.0%
    376
    +0.13
    0.7%
    329
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    329
    +0.18
    0.02
    465
    +0.13
    0.02
    122
    +0.11
    0.02
    Negative Logits
    ³
    -2.74
    £
    -2.60
    §
    -2.40
    Ń
    -2.38
    ĥ
    -2.06
    µ
    -2.05
    ·
    -2.04
    ĵ
    -2.03
    ĥ½
    -1.96
    ĨĴ
    -1.94
    POSITIVE LOGITS
    hole
    1.90
    facts
    1.53
    holes
    1.48
    grass
    1.44
    oon
    1.44
     pains
    1.43
    acre
    1.43
    istically
    1.42
    ually
    1.39
    bud
    1.39
    Activations Density 0.017%

    No Known Activations