© 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. 23986
    Prev
    Next
    INDEX
    Explanations

    references related to legal terminology and court proceedings

    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
    143
    +0.15
    0.8%
    392
    +0.13
    0.7%
    500
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    392
    +0.15
    0.13
    500
    +0.13
    0.07
    33
    +0.12
    0.08
    Negative Logits
    ĻĤ
    -2.34
    ¬
    -2.09
    ħ
    -1.85
    ī
    -1.66
    ŀ
    -1.59
    ģ
    -1.58
    mina
    -1.57
    ľ
    -1.57
    ¡
    -1.56
    «
    -1.51
    POSITIVE LOGITS
    acea
    1.44
    destruct
    1.42
    oretical
    1.41
    efficient
    1.40
    dream
    1.40
    abstract
    1.38
    practice
    1.35
    illar
    1.33
    optera
    1.32
    omb
    1.30
    Activations Density 2.972%

    No Known Activations