© 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
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 0-MLP-SM
    6. 27113
    Prev
    Next
    INDEX
    Explanations

    references to laws or regulations regarding corporate structures and responsibilities

    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
    23
    +0.19
    1.4%
    53
    +0.16
    1.1%
    438
    +0.14
    1.0%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    53
    +0.19
    0.42
    438
    +0.16
    0.39
    56
    +0.14
    0.11
    Negative Logits
     Stats
    -1.46
     accelerator
    -1.40
    ición
    -1.35
    icode
    -1.33
    ('',
    -1.32
     cont
    -1.27
    asion
    -1.26
     area
    -1.24
     GENERATED
    -1.22
    chini
    -1.22
    POSITIVE LOGITS
    §
    2.29
    ĥ½
    2.21
    ĨĴ
    2.19
    Ļª
    2.08
    Ĵ
    2.06
    ŀ
    1.98
    Ĥ
    1.94
    Ī
    1.93
    ĺ
    1.89
    Ĺ
    1.88
    Activations Density 13.470%

    No Known Activations