© 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. 25558
    Prev
    Next
    INDEX
    Explanations

    the phrase "These 10" to indicate specific examples or items listed in a text

    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
    433
    +0.15
    0.9%
    199
    +0.14
    0.8%
    18
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    279
    +0.15
    0.07
    208
    +0.14
    0.05
    186
    +0.13
    0.05
    Negative Logits
    ster
    -1.57
     season
    -1.52
     lovers
    -1.51
    ´
    -1.50
    ¼
    -1.47
     Us
    -1.42
    sters
    -1.37
     misplaced
    -1.35
    Culture
    -1.34
    elo
    -1.34
    POSITIVE LOGITS
     discharg
    1.71
    ubern
    1.61
     repr
    1.59
    iginally
    1.58
    oms
    1.55
    fficients
    1.54
     elapsed
    1.54
    oped
    1.45
     abortions
    1.44
    orms
    1.43
    Activations Density 0.089%

    No Known Activations