© 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. 27092
    Prev
    Next
    INDEX
    Explanations

    references to accidents and incidents

    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
    +0.13
    0.7%
    184
    +0.12
    0.6%
    376
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    184
    +0.13
    0.02
    241
    +0.12
    0.02
    204
    +0.11
    0.01
    Negative Logits
    ł
    -3.38
    ı
    -3.22
    ¥
    -3.17
    ij
    -3.08
    ¸
    -3.06
    ļ
    -3.06
    ¹
    -3.03
    ĸ
    -3.00
    ¡
    -2.98
    ĥ½
    -2.98
    POSITIVE LOGITS
    autre
    1.52
    idone
    1.51
    ystems
    1.48
    iamo
    1.48
    zione
    1.48
    ionale
    1.47
    icum
    1.46
    acea
    1.44
    osidase
    1.44
    iscus
    1.43
    Activations Density 0.015%

    No Known Activations