© 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. 22874
    Prev
    Next
    INDEX
    Explanations

    references to court proceedings or legal contexts

    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
    497
    +0.16
    0.9%
    414
    +0.14
    0.8%
    47
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    414
    +0.16
    0.02
    497
    +0.14
    0.01
    445
    +0.12
    0.01
    Negative Logits
    head
    -1.55
     my
    -1.49
    HEAD
    -1.46
     snakes
    -1.46
    documentclass
    -1.45
     diligence
    -1.39
     je
    -1.37
     WARRANTY
    -1.37
    */
    -1.32
     vac
    -1.31
    POSITIVE LOGITS
    ellular
    1.85
    teenth
    1.61
    hed
    1.48
    hered
    1.46
    itable
    1.43
     predictor
    1.37
    cyt
    1.36
    entric
    1.35
    ¿½
    1.34
    lected
    1.31
    Activations Density 0.177%

    No Known Activations