© 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 EvalsExportsAPI 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. 28996
    Prev
    Next
    INDEX
    Explanations

    instances of the word "recruited"

    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
    +0.22
    1.3%
    156
    +0.20
    1.2%
    148
    +0.17
    1.0%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    48
    +0.22
    0.01
    148
    +0.20
    0.01
    351
    +0.17
    0.01
    Negative Logits
     celebrated
    -1.88
    pired
    -1.66
     dass
    -1.56
     present
    -1.54
    ikh
    -1.53
    ĨĴ
    -1.52
     pronounced
    -1.49
     history
    -1.45
     drastic
    -1.38
     commemor
    -1.34
    POSITIVE LOGITS
    stance
    1.59
    ulses
    1.57
    ently
    1.57
    fail
    1.54
    erably
    1.54
    age
    1.52
    stown
    1.51
    ressing
    1.40
    itus
    1.39
    aneously
    1.37
    Activations Density 0.007%

    No Known Activations