© 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. 26341
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal or formal contexts

    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
    5
    +0.12
    0.7%
    422
    +0.12
    0.7%
    329
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    422
    +0.12
    0.01
    5
    +0.12
    0.01
    329
    +0.10
    0.01
    Negative Logits
    ellow
    -1.42
    HECK
    -1.40
     whistle
    -1.38
    odor
    -1.36
     handsome
    -1.34
    ands
    -1.33
     temper
    -1.32
     developing
    -1.32
    return
    -1.32
    strict
    -1.31
    POSITIVE LOGITS
    eno
    1.98
    icions
    1.82
    endas
    1.82
    izes
    1.75
    enos
    1.71
    ues
    1.66
    ystems
    1.65
    ición
    1.64
    idone
    1.61
    Pane
    1.57
    Activations Density 0.035%

    No Known Activations