© 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. 25597
    Prev
    Next
    INDEX
    Explanations

    phrases related to formal proposals or interventions

    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
    +0.15
    0.9%
    276
    +0.13
    0.8%
    177
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    441
    +0.15
    0.01
    378
    +0.13
    0.01
    177
    +0.13
    0.01
    Negative Logits
     resignation
    -1.82
    ľ
    -1.82
     rude
    -1.71
    bey
    -1.69
    >';
    -1.66
     happier
    -1.64
    >'
    -1.64
    ĥ½
    -1.64
    woke
    -1.63
     resigned
    -1.63
    POSITIVE LOGITS
    grounds
    2.13
    nel
    2.12
    ally
    2.08
    aho
    1.93
    naire
    1.92
    ary
    1.88
    ista
    1.81
    ist
    1.81
    ifacts
    1.78
    aries
    1.75
    Activations Density 0.011%

    No Known Activations