© 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. 26806
    Prev
    Next
    INDEX
    Explanations

    instances of the word "trailing" and phrases involving "chasing."

    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
    115
    +0.15
    0.9%
    22
    +0.14
    0.8%
    376
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    135
    +0.15
    0.01
    22
    +0.14
    0.01
    416
    +0.13
    0.01
    Negative Logits
    »¿
    -2.62
    ĥ½
    -2.58
    ¦
    -2.58
    §
    -2.52
    ı
    -2.48
    ļ
    -2.40
           ↵
    -2.38
    <|outofrange|>
    -2.38
    ↵  ³³³
    -2.38
    č↵
    -2.38
    POSITIVE LOGITS
    ATCC
    1.54
    )](#
    1.52
    ento
    1.51
    pha
    1.50
    )].
    1.45
    olin
    1.45
    gap
    1.44
    \][
    1.44
     ]"
    1.41
    orph
    1.41
    Activations Density 0.029%

    No Known Activations