© 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. 28808
    Prev
    Next
    INDEX
    Explanations

    instances of the word "sought" in various 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
    376
    +0.21
    1.2%
    463
    +0.17
    1.0%
    73
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    463
    +0.21
    0.03
    73
    +0.17
    0.02
    48
    +0.11
    0.02
    Negative Logits
    ferroni
    -1.57
    ened
    -1.54
    Populated
    -1.53
    ens
    -1.36
    ksen
    -1.35
     expected
    -1.34
    enson
    -1.33
    omorphism
    -1.32
    en
    -1.32
     pronounced
    -1.31
    POSITIVE LOGITS
     refuge
    2.00
     unsuccess
    1.92
    veis
    1.64
    bels
    1.51
    gery
    1.50
    posts
    1.49
    geant
    1.47
     sanctuary
    1.42
    eker
    1.41
    ģ
    1.38
    Activations Density 0.006%

    No Known Activations