© 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. 0-MLP-SM
    11. 27106
    Prev
    Next
    INDEX
    Explanations

    name entities and formal references related to Texas 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/0-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.0.hook_mlp_out
    Hook Layer
    0
    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
    111
    +0.18
    1.0%
    245
    +0.13
    0.7%
    18
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.18
    0.02
    261
    +0.13
    0.01
    245
    +0.12
    0.01
    Negative Logits
     taken
    -1.75
    '?"
    -1.67
    ';
    -1.65
    '?
    -1.50
     connecting
    -1.49
     reviewed
    -1.49
     purchased
    -1.48
     ?"
    -1.46
     crossed
    -1.46
     ')
    -1.44
    POSITIVE LOGITS
    rooms
    1.99
     ranks
    1.85
    Ĵ
    1.73
    itives
    1.70
    tah
    1.64
    Ĭ
    1.63
    rams
    1.58
    fileID
    1.56
    room
    1.54
     rounds
    1.53
    Activations Density 0.013%

    No Known Activations