Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 0-MLP-SM
    6. 27446
    Prev
    Next
    INDEX
    Explanations

    instances of the word "become"

    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
    +0.19
    1.1%
    376
    +0.17
    1.0%
    304
    +0.15
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    304
    +0.19
    0.05
    193
    +0.17
    0.04
    240
    +0.15
    0.03
    Negative Logits
    lor
    -1.62
    inho
    -1.54
    ierno
    -1.50
    ail
    -1.49
    isesti
    -1.49
    ounded
    -1.49
    ----------------------------------------------------------------------------------------------------------------
    -1.46
    ERY
    -1.44
    seys
    -1.42
    -----------------
    -1.42
    POSITIVE LOGITS
    ¼
    2.76
    ¶
    2.50
    °
    2.27
    «
    2.25
    IJ
    2.19
    ²
    2.17
    ¨
    2.09
    Ĩ
    2.07
    µ
    2.07
    Ĭ
    2.06
    Activations Density 3.096%

    No Known Activations