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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 22737
    Prev
    Next
    INDEX
    Explanations

    legal terminology and references within legal documents

    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
    156
    +0.17
    1.0%
    171
    +0.16
    0.9%
    66
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.17
    0.06
    171
    +0.16
    0.01
    316
    +0.12
    0.09
    Negative Logits
    ĥ½
    -2.42
    ī
    -2.38
    Ŀ
    -2.36
    ·
    -2.25
    ¼
    -2.22
    ı
    -2.18
    ľĵ
    -2.18
    ŀ
    -2.17
    »¿
    -2.15
    ľ
    -2.13
    POSITIVE LOGITS
    qrt
    1.58
    /+
    1.50
    +^
    1.47
    etric
    1.47
    ^--
    1.45
    idelity
    1.44
    eous
    1.43
    ployment
    1.43
    ^**
    1.40
    velopment
    1.39
    Activations Density 1.865%

    No Known Activations