© 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. 2-MLP-SM
    11. 23969
    Prev
    Next
    INDEX
    Explanations

    references to archives or collections of items

    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
    156
    +0.35
    2.1%
    282
    +0.12
    0.7%
    223
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    277
    +0.35
    0.05
    55
    +0.12
    0.03
    78
    +0.12
    0.01
    Negative Logits
    endl
    -1.48
    rvert
    -1.43
    INT
    -1.38
    Äij
    -1.37
    NON
    -1.36
    uw
    -1.35
    ¶
    -1.35
    llll
    -1.34
    findViewById
    -1.32
    UH
    -1.31
    POSITIVE LOGITS
     sparing
    1.81
     mechanism
    1.53
     principle
    1.52
     law
    1.45
     predicate
    1.41
     campaign
    1.41
     senators
    1.39
     union
    1.38
     defense
    1.36
     defence
    1.36
    Activations Density 0.477%

    No Known Activations