© 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. 30223
    Prev
    Next
    INDEX
    Explanations

    references to the concept of the Holy Spirit

    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
    +0.19
    1.1%
    128
    +0.12
    0.7%
    376
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    128
    +0.19
    0.01
    506
    +0.12
    0.01
    27
    +0.11
    0.01
    Negative Logits
    ¯
    -2.47
    Į
    -2.27
    ®
    -2.20
    ¬
    -2.16
    ħ
    -2.10
    ĥ½
    -1.98
    ij
    -1.96
    ľĵ
    -1.92
    ¶
    -1.90
    §
    -1.90
    POSITIVE LOGITS
    ual
    2.13
    bilt
    1.94
    uality
    1.92
    aho
    1.86
    uel
    1.84
    bank
    1.74
    horse
    1.73
    stown
    1.67
    uous
    1.65
    ilee
    1.61
    Activations Density 0.011%

    No Known Activations