© 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. 28204
    Prev
    Next
    INDEX
    Explanations

    references to legal concepts or terminology

    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
    352
    +0.13
    0.7%
    114
    +0.13
    0.7%
    119
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    114
    +0.13
    0.06
    352
    +0.13
    0.06
    180
    +0.12
    0.05
    Negative Logits
     Nation
    -1.72
     whole
    -1.59
     racial
    -1.56
     sweat
    -1.46
     happier
    -1.41
    EVER
    -1.41
     nation
    -1.40
    thood
    -1.36
     racist
    -1.35
     sudden
    -1.35
    POSITIVE LOGITS
    ģ
    1.92
    gio
    1.90
    olver
    1.82
    books
    1.81
    break
    1.79
    fully
    1.79
    smith
    1.77
    doms
    1.76
    breaker
    1.75
    master
    1.74
    Activations Density 1.462%

    No Known Activations