© 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. 25312
    Prev
    Next
    INDEX
    Explanations

    terms related to weight categories and classifications

    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
    376
    +0.14
    0.8%
    29
    +0.10
    0.6%
    481
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    481
    +0.14
    0.02
    293
    +0.10
    0.02
    232
    +0.10
    0.01
    Negative Logits
     meaning
    -1.64
     peace
    -1.50
     Spacewatch
    -1.48
     say
    -1.45
     Peace
    -1.44
    anian
    -1.43
     Copyright
    -1.40
    áĢº
    -1.40
     Shore
    -1.40
     tears
    -1.39
    POSITIVE LOGITS
    naire
    1.92
    ière
    1.80
    ahead
    1.75
     arsenal
    1.67
    ings
    1.65
    ÅĽci
    1.60
    achusetts
    1.54
    strap
    1.53
    igent
    1.51
    case
    1.50
    Activations Density 0.026%

    No Known Activations