© 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
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. MLP Post
    9. 0-MLP-SM
    11. 26997
    Prev
    Next
    INDEX
    Explanations

    the word "this" in various contexts

    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
    238
    +0.11
    0.6%
    376
    +0.10
    0.6%
    94
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    402
    +0.11
    0.15
    26
    +0.10
    0.14
    199
    +0.10
    0.14
    Negative Logits
    İ
    -1.99
    ĩ
    -1.78
    Ĭ
    -1.75
    Ĵ
    -1.55
    ffect
    -1.55
    between
    -1.53
    wheel
    -1.48
    whe
    -1.48
    ĵ
    -1.48
    ĥ
    -1.46
    POSITIVE LOGITS
    findViewById
    1.92
    ary
    1.83
    blockList
    1.82
    aires
    1.54
    endants
    1.54
    aries
    1.53
    jsfiddle
    1.53
    ientes
    1.50
     findViewById
    1.49
     annealing
    1.49
    Activations Density 0.273%

    No Known Activations