© 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. 28440
    Prev
    Next
    INDEX
    Explanations

    instances of commas

    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
    94
    +0.16
    0.9%
    347
    +0.15
    0.8%
    363
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    203
    +0.16
    0.36
    23
    +0.15
    0.31
    494
    +0.11
    0.25
    Negative Logits
    blogger
    -1.70
    anese
    -1.63
    TTP
    -1.61
    ENA
    -1.59
     âĻª
    -1.57
    thens
    -1.51
    agus
    -1.48
    disambiguation
    -1.47
    gments
    -1.45
     Wow
    -1.45
    POSITIVE LOGITS
    £
    2.42
    ĺ
    2.24
    ij
    2.17
    ĥ½
    2.13
    ³
    2.08
    ¶
    2.03
    ½
    2.00
    µ
    1.97
    ¾
    1.95
    Ŀ
    1.90
    Activations Density 3.099%

    No Known Activations