© 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. 30434
    Prev
    Next
    INDEX
    Explanations

    instances of the term "diff" related to differences in code or data

    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
    142
    +0.14
    0.8%
    348
    +0.12
    0.7%
    0
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    142
    +0.14
    0.02
    324
    +0.12
    0.02
    0
    +0.12
    0.01
    Negative Logits
    Ĥ
    -2.07
    ĵ
    -2.00
    ķ
    -1.98
    Ĭ
    -1.95
    ĸ´
    -1.85
    ´
    -1.84
    Ĩ
    -1.82
    ı
    -1.76
    Ĥ¬
    -1.74
    Ľ
    -1.72
    POSITIVE LOGITS
    :`
    2.06
    minist
    1.99
    icile
    1.91
    gren
    1.81
    etable
    1.80
    vier
    1.74
    eria
    1.73
    icult
    1.71
    optimal
    1.69
    edin
    1.68
    Activations Density 0.012%

    No Known Activations