© 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. 25587
    Prev
    Next
    INDEX
    Explanations

    repeated instances of the letter 'W'

    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
    369
    +0.22
    1.3%
    219
    +0.12
    0.7%
    358
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    313
    +0.22
    0.05
    0
    +0.12
    0.05
    388
    +0.11
    0.05
    Negative Logits
     sure
    -1.82
     yours
    -1.70
    acity
    -1.52
    imit
    -1.50
    acious
    -1.49
     true
    -1.44
     apologize
    -1.42
    ities
    -1.42
     your
    -1.42
    acion
    -1.38
    POSITIVE LOGITS
    ¤
    2.46
    Ĥ¬
    2.38
    Ľ
    2.35
    į
    2.25
    ĸ
    2.22
    Ķ
    2.19
    ®
    2.13
    £
    2.01
    Ĵ
    1.99
    ĻĤ
    1.99
    Activations Density 1.331%

    No Known Activations