© 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
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 2-MLP-SM
    6. 26535
    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
    82
    +0.13
    0.8%
    247
    +0.13
    0.7%
    355
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    474
    +0.13
    0.02
    355
    +0.13
    0.04
    128
    +0.11
    0.01
    Negative Logits
    agraph
    -1.79
     review
    -1.67
     acres
    -1.65
    ellee
    -1.58
     notice
    -1.55
     confidential
    -1.51
    rael
    -1.50
     publicity
    -1.49
     PUBL
    -1.48
    anta
    -1.48
    POSITIVE LOGITS
     converges
    1.65
     themselves
    1.52
    chitz
    1.51
    sembles
    1.48
     equations
    1.48
    för
    1.47
     Equations
    1.45
     itself
    1.45
     drills
    1.38
     imposed
    1.38
    Activations Density 0.282%

    No Known Activations