© 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. 2-MLP-SM
    11. 26776
    Prev
    Next
    INDEX
    Explanations

    legal terminology and references to 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
    165
    +0.12
    0.6%
    126
    +0.11
    0.6%
    216
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    207
    +0.12
    0.02
    165
    +0.11
    0.03
    38
    +0.10
    0.00
    Negative Logits
     warrant
    -1.52
     persons
    -1.48
     warrants
    -1.43
    dismiss
    -1.42
     lit
    -1.41
    ![(
    -1.39
    itor
    -1.36
     prosec
    -1.34
    address
    -1.32
    stated
    -1.32
    POSITIVE LOGITS
    ainen
    1.59
    heit
    1.57
    Ĵ
    1.51
    riors
    1.49
    Ĩ
    1.48
    ERY
    1.48
    asia
    1.47
    schemas
    1.44
     Ont
    1.43
    ļ
    1.37
    Activations Density 0.204%

    No Known Activations