© 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. 29984
    Prev
    Next
    INDEX
    Explanations

    references to personal details or personal information

    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
    391
    +0.13
    0.8%
    156
    +0.12
    0.7%
    365
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    277
    +0.13
    0.01
    391
    +0.12
    0.01
    223
    +0.12
    0.01
    Negative Logits
     face
    -1.57
    rian
    -1.54
    odor
    -1.47
     wake
    -1.47
     him
    -1.42
     entirety
    -1.41
    unt
    -1.41
    ÑĢÑĭ
    -1.40
     answer
    -1.38
    "`
    -1.37
    POSITIVE LOGITS
    ties
    1.77
    sheet
    1.73
    craft
    1.69
    aic
    1.67
    isms
    1.60
    bow
    1.59
    istry
    1.59
    isations
    1.59
     accounts
    1.57
    iary
    1.57
    Activations Density 0.010%

    No Known Activations