© 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. 30288
    Prev
    Next
    INDEX
    Explanations

    references to mills and milling processes

    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
    427
    +0.13
    0.7%
    245
    +0.12
    0.7%
    376
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    427
    +0.13
    0.01
    264
    +0.12
    0.01
    128
    +0.12
    0.01
    Negative Logits
    Ĥ
    -2.70
    ¯
    -2.67
    ³
    -2.56
    ·¸
    -2.47
    ¿
    -2.42
    Ŀ
    -2.37
    ĻĤ
    -2.27
    ľĵ
    -2.19
    ķ
    -2.17
    Ĩ
    -2.15
    POSITIVE LOGITS
    ikel
    2.09
    isecond
    2.07
    enium
    1.99
    imeter
    1.96
    ton
    1.94
    stone
    1.90
    anguage
    1.87
    wright
    1.82
    stones
    1.75
    hart
    1.73
    Activations Density 0.128%

    No Known Activations