© 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. 30183
    Prev
    Next
    INDEX
    Explanations

    words associated with a specific visual element or branding guideline

    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
    410
    +0.15
    0.9%
    286
    +0.13
    0.7%
    162
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    410
    +0.15
    0.01
    468
    +0.13
    0.01
    341
    +0.13
    0.01
    Negative Logits
     apologize
    -1.50
     '</
    -1.48
    visiae
    -1.47
     </
    -1.47
    cause
    -1.45
     searched
    -1.44
     succeeding
    -1.43
     ':
    -1.42
    where
    -1.42
    č↵
    -1.41
    POSITIVE LOGITS
    ulators
    1.71
    ulated
    1.66
    fest
    1.58
    ulator
    1.56
     palate
    1.53
    pel
    1.50
    ulatory
    1.46
    ulate
    1.40
    mouth
    1.38
    lens
    1.38
    Activations Density 0.257%

    No Known Activations