© 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 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. 29257
    Prev
    Next
    INDEX
    Explanations

    references to the Supreme Court

    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
    244
    +0.13
    0.8%
    397
    +0.11
    0.7%
    505
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    244
    +0.13
    0.01
    58
    +0.11
    0.01
    505
    +0.11
    0.01
    Negative Logits
    ĥ½
    -1.94
    \)
    -1.85
    ¿½
    -1.64
     ')
    -1.61
     closed
    -1.45
     modified
    -1.45
    'd
    -1.45
     hypothesis
    -1.43
     relation
    -1.43
     joined
    -1.41
    POSITIVE LOGITS
    rooms
    2.07
    etable
    1.92
    sheet
    1.87
    books
    1.86
    cript
    1.82
    ÃŃvel
    1.80
    áĢ¸
    1.79
    writers
    1.78
    room
    1.78
    heets
    1.77
    Activations Density 0.008%

    No Known Activations