© 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. 28999
    Prev
    Next
    INDEX
    Explanations

    instances of the word "lying" or related forms indicating deceit or falsehood

    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
    +0.15
    0.9%
    22
    +0.15
    0.9%
    111
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    22
    +0.15
    0.01
    338
    +0.15
    0.01
    19
    +0.10
    0.01
    Negative Logits
    »¿
    -1.85
    ¦
    -1.68
    Ļª
    -1.66
    Ĺ
    -1.57
    ¨
    -1.57
    Ĥ
    -1.52
    itably
    -1.49
    withstanding
    -1.47
    ¿½
    -1.47
    athing
    -1.46
    POSITIVE LOGITS
    tons
    1.92
    roup
    1.76
     apparatus
    1.67
     machine
    1.67
     facility
    1.65
     torque
    1.62
     luciferase
    1.62
     checkpoint
    1.61
     capability
    1.59
     cavity
    1.59
    Activations Density 4.703%

    No Known Activations