© 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. 29928
    Prev
    Next
    INDEX
    Explanations

    corporate names or mentions of corporations

    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
    +0.22
    1.3%
    245
    +0.14
    0.8%
    91
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    245
    +0.22
    0.02
    370
    +0.14
    0.01
    91
    +0.12
    0.01
    Negative Logits
    ĥ½
    -2.25
    tica
    -1.54
    IJ
    -1.53
    OOGLE
    -1.52
    ĨĴ
    -1.52
    ĥ
    -1.50
    Ĥ¬
    -1.50
     sexes
    -1.50
    ³
    -1.48
    ophagus
    -1.48
    POSITIVE LOGITS
    ulent
    2.22
    ulence
    1.82
    ycin
    1.80
     controls
    1.78
    isión
    1.59
    ult
    1.58
    ious
    1.57
    amental
    1.50
    ial
    1.46
    ariat
    1.46
    Activations Density 0.014%

    No Known Activations