© 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. 28231
    Prev
    Next
    INDEX
    Explanations

    references to detectors or detection systems

    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
    123
    +0.13
    0.7%
    376
    +0.10
    0.6%
    156
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    123
    +0.13
    0.01
    198
    +0.10
    0.01
    370
    +0.10
    0.01
    Negative Logits
    ĥ½
    -2.18
    ı
    -2.08
    ¿½
    -1.98
    ³
    -1.90
    Ĥ¬
    -1.89
    soever
    -1.85
    Ķ
    -1.79
    ¦
    -1.69
    Ĥ
    -1.66
    ¸
    -1.65
    POSITIVE LOGITS
    ally
    1.86
    nikov
    1.83
    al
    1.70
    als
    1.66
    iom
    1.66
    anguage
    1.64
    ism
    1.61
    rams
    1.61
    ary
    1.61
    stadt
    1.60
    Activations Density 0.012%

    No Known Activations