© 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. 0-MLP-SM
    11. 25761
    Prev
    Next
    INDEX
    Explanations

    references to breast density

    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
    156
    +0.20
    1.2%
    362
    +0.17
    1.0%
    376
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    448
    +0.20
    0.01
    255
    +0.17
    0.01
    90
    +0.12
    0.01
    Negative Logits
    tingham
    -1.63
    ureus
    -1.62
    onomic
    -1.44
     proceeded
    -1.41
    derer
    -1.41
    return
    -1.41
    symmetric
    -1.38
    anson
    -1.37
     enter
    -1.34
    acity
    -1.34
    POSITIVE LOGITS
    idelines
    1.73
    ¢
    1.68
    enough
    1.57
     defense
    1.47
    £
    1.43
    France
    1.43
     enough
    1.43
    ļ
    1.42
     prison
    1.40
    erals
    1.40
    Activations Density 0.012%

    No Known Activations