© 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. 26228
    Prev
    Next
    INDEX
    Explanations

    terms related to the process of homogenization

    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
    182
    +0.15
    0.9%
    125
    +0.14
    0.8%
    184
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    182
    +0.15
    0.01
    229
    +0.14
    0.01
    125
    +0.12
    0.01
    Negative Logits
     preponderance
    -1.74
     choice
    -1.57
     utmost
    -1.57
     magnitude
    -1.54
     slightest
    -1.54
     APPEALS
    -1.53
    dition
    -1.47
     totality
    -1.45
     selective
    -1.45
     necessity
    -1.43
    POSITIVE LOGITS
    iliar
    2.02
    ynom
    1.90
    ophone
    1.88
    ious
    1.88
    iative
    1.86
    ÃŃas
    1.82
    uar
    1.77
    icians
    1.75
    iste
    1.74
    uary
    1.69
    Activations Density 0.018%

    No Known Activations