© 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. 30015
    Prev
    Next
    INDEX
    Explanations

    terminology related to anesthesia and its effects on living beings

    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
    376
    +0.13
    0.7%
    2
    +0.10
    0.6%
    46
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    46
    +0.13
    0.01
    315
    +0.10
    0.01
    482
    +0.10
    0.01
    Negative Logits
    Ķ
    -3.25
    ĥ½
    -3.12
    IJ
    -2.94
    ķ
    -2.90
    ħ
    -2.88
    ĥ
    -2.85
    ¯
    -2.80
    į
    -2.76
    ·¸
    -2.69
    ĭ
    -2.68
    POSITIVE LOGITS
    erve
    1.65
     positions
    1.64
    shots
    1.63
    don
    1.58
    sci
    1.55
    imeter
    1.51
    ilate
    1.50
     shots
    1.49
     sessions
    1.48
    mond
    1.48
    Activations Density 0.005%

    No Known Activations