© 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 EvalsExportsAPI 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. 29204
    Prev
    Next
    INDEX
    Explanations

    repetitive phrases or ideas expressing continuation or similarity

    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
    137
    +0.15
    0.8%
    320
    +0.11
    0.6%
    65
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    239
    +0.15
    0.05
    359
    +0.11
    0.05
    199
    +0.11
    0.04
    Negative Logits
    anese
    -1.87
     purposes
    -1.77
    ĻĤ
    -1.68
    anium
    -1.63
    jdbc
    -1.60
    amycin
    -1.60
    schemas
    -1.59
     Syndrome
    -1.51
    anos
    -1.50
    iella
    -1.49
    POSITIVE LOGITS
    hood
    1.69
    pt
    1.60
     dozen
    1.59
    pm
    1.54
    number
    1.54
    LT
    1.53
     Kitty
    1.45
    friend
    1.40
    hip
    1.34
    lette
    1.34
    Activations Density 0.027%

    No Known Activations