© 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. 29723
    Prev
    Next
    INDEX
    Explanations

    words related to colors

    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
    +0.14
    0.8%
    493
    +0.12
    0.6%
    296
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    384
    +0.14
    0.01
    493
    +0.12
    0.02
    296
    +0.11
    0.01
    Negative Logits
     dissolved
    -1.59
     maintained
    -1.49
     towel
    -1.48
     sanctioned
    -1.48
     restrained
    -1.46
    eded
    -1.45
     pleased
    -1.43
     prohibited
    -1.43
     warmed
    -1.42
    sed
    -1.40
    POSITIVE LOGITS
    ista
    1.60
    rive
    1.57
    ĻĤ
    1.51
    emption
    1.50
    holm
    1.48
    efined
    1.47
    –
    1.44
    etermined
    1.39
    etect
    1.39
    emente
    1.38
    Activations Density 0.021%

    No Known Activations