© 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. 27028
    Prev
    Next
    INDEX
    Explanations

    instances of the word "As" indicating a cause or reasoning

    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
    424
    +0.21
    1.2%
    502
    +0.13
    0.8%
    376
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    424
    +0.21
    0.09
    459
    +0.13
    0.05
    192
    +0.12
    0.05
    Negative Logits
     ...
    -1.50
     them
    -1.45
    itud
    -1.44
    But
    -1.44
    č
    -1.41
    Instead
    -1.41
    raising
    -1.39
    eff
    -1.38
     âĢ¦
    -1.37
    Category
    -1.36
    POSITIVE LOGITS
    ¾
    3.38
    ¶
    3.20
    µ
    3.09
    ¹
    3.04
    ²
    2.96
    ¸
    2.94
    ¼
    2.82
    Ĥ
    2.81
    ↵
    2.78
    2.78
    Activations Density 3.672%

    No Known Activations