© 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. 25878
    Prev
    Next
    INDEX
    Explanations

    references to business professionals and their roles

    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
    156
    +0.34
    2.1%
    376
    +0.14
    0.9%
    494
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    156
    +0.34
    0.02
    271
    +0.14
    0.01
    127
    +0.14
    0.02
    Negative Logits
    ĥ½
    -1.76
    º
    -1.62
    pless
    -1.59
     Postal
    -1.57
    ¬
    -1.53
    ij
    -1.51
    Ŀ
    -1.44
     Province
    -1.39
    ERT
    -1.38
    »
    -1.36
    POSITIVE LOGITS
    ials
    2.04
    ially
    2.02
    ielle
    1.91
    ships
    1.84
    ulent
    1.68
     outwe
    1.66
    iac
    1.65
    ically
    1.64
     meets
    1.59
    iously
    1.59
    Activations Density 0.037%

    No Known Activations