© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 0-MLP-SM
    6. 27848
    Prev
    Next
    INDEX
    Explanations

    special characters or unique symbols

    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
    330
    +0.17
    1.0%
    410
    +0.16
    0.9%
    111
    +0.15
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    330
    +0.17
    0.01
    111
    +0.16
    0.01
    410
    +0.15
    0.01
    Negative Logits
    Ħ
    -1.68
    ĺ
    -1.65
    iero
    -1.48
    °
    -1.48
    ķ
    -1.45
    asis
    -1.43
    ural
    -1.37
    ĥ
    -1.36
     prediction
    -1.32
     malfunction
    -1.27
    POSITIVE LOGITS
    shire
    1.69
    nut
    1.56
    ringe
    1.52
    bars
    1.50
    rails
    1.40
    wolf
    1.39
    iest
    1.38
    vi
    1.36
    ---|---
    1.34
    iate
    1.32
    Activations Density 0.012%

    No Known Activations