Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 0-MLP-SM
    6. 27408
    Prev
    Next
    INDEX
    Explanations

    references to advantages or benefits

    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%
    206
    +0.12
    0.7%
    241
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    206
    +0.14
    0.02
    453
    +0.12
    0.02
    406
    +0.11
    0.02
    Negative Logits
    sel
    -1.80
    affe
    -1.61
    ORE
    -1.50
    ĨĴ
    -1.45
    ness
    -1.45
    ANI
    -1.42
    seys
    -1.42
    DU
    -1.41
    nbsp
    -1.41
     Edited
    -1.40
    POSITIVE LOGITS
     radius
    1.84
    ously
    1.80
     territory
    1.65
     trees
    1.58
     radii
    1.47
     area
    1.47
     compartments
    1.47
    ways
    1.46
     areas
    1.46
     crops
    1.44
    Activations Density 0.029%

    No Known Activations