© 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. 29763
    Prev
    Next
    INDEX
    Explanations

    references to legal proceedings or court cases

    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
    505
    +0.14
    0.9%
    161
    +0.11
    0.7%
    343
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    505
    +0.14
    0.02
    161
    +0.11
    0.02
    398
    +0.10
    0.02
    Negative Logits
     leisure
    -1.63
     dex
    -1.62
     relation
    -1.61
    xy
    -1.54
    )](#
    -1.53
     pity
    -1.51
    utenant
    -1.50
    \)
    -1.50
     dependence
    -1.49
    ]{.
    -1.48
    POSITIVE LOGITS
    heets
    2.44
    pieces
    2.20
    heet
    2.14
    cript
    2.04
    ista
    2.02
    ¾
    2.00
    ister
    1.98
    áĢ¸
    1.92
    rooms
    1.90
    helf
    1.88
    Activations Density 0.129%

    No Known Activations