© 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. 28763
    Prev
    Next
    INDEX
    Explanations

    references to psychological and existential concepts

    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
    +0.28
    1.7%
    71
    +0.11
    0.7%
    63
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    156
    +0.28
    0.01
    506
    +0.11
    0.01
    320
    +0.10
    0.01
    Negative Logits
     cruel
    -1.57
    agles
    -1.56
    xico
    -1.53
    idegger
    -1.48
     publish
    -1.47
    isenberg
    -1.41
     reconsider
    -1.40
    rocy
    -1.40
     deadly
    -1.39
     discuss
    -1.39
    POSITIVE LOGITS
    het
    1.51
    ĻĤ
    1.49
    ulence
    1.48
    heta
    1.45
    icile
    1.43
    ichlet
    1.43
    ignment
    1.41
    ist
    1.41
    s
    1.40
    ulator
    1.37
    Activations Density 0.015%

    No Known Activations