© 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. 25405
    Prev
    Next
    INDEX
    Explanations

    references to autobiographies and memoirs

    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
    +0.30
    1.8%
    23
    +0.17
    1.0%
    177
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    156
    +0.30
    0.04
    177
    +0.17
    0.03
    148
    +0.13
    0.02
    Negative Logits
     Collaboration
    -1.56
    gaard
    -1.53
    arner
    -1.50
     initiative
    -1.49
    ENER
    -1.45
     controls
    -1.44
    iej
    -1.41
     inhibitor
    -1.40
    bsd
    -1.40
    forum
    -1.39
    POSITIVE LOGITS
    {"
    1.54
    textup
    1.47
    odot
    1.45
     vivid
    1.38
     suffice
    1.36
     mine
    1.35
    ↵
    1.35
    textrm
    1.33
    {
    1.33
    soever
    1.33
    Activations Density 0.118%

    No Known Activations