© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. MLP Post
    9. 2-MLP-SM
    11. 26522
    Prev
    Next
    INDEX
    Explanations

    legal terms related to contracts and agreements

    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/2-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.2.hook_mlp_out
    Hook Layer
    2
    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
    +0.25
    1.4%
    253
    +0.13
    0.8%
    438
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    50
    +0.25
    0.06
    102
    +0.13
    0.05
    92
    +0.13
    0.06
    Negative Logits
    ÃŃa
    -2.10
    osti
    -2.07
    rection
    -1.67
    ressor
    -1.66
    rected
    -1.65
    Å¡ÃŃ
    -1.64
    illon
    -1.63
    ost
    -1.62
    etry
    -1.58
    ÃŃan
    -1.56
    POSITIVE LOGITS
    ĺ
    3.59
    Ĥ
    3.30
    ı
    3.21
    ĵ
    3.17
    İ
    3.13
    ·¸
    3.09
    ¾
    3.07
    ±
    3.06
    ł
    3.06
    ¦
    3.05
    Activations Density 1.131%

    No Known Activations