© 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 EvalsExportsAPI 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. 29369
    Prev
    Next
    INDEX
    Explanations

    phrases that use the word "ending."

    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
    +0.11
    0.6%
    176
    +0.10
    0.6%
    55
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    55
    +0.11
    0.02
    465
    +0.10
    0.01
    176
    +0.10
    0.01
    Negative Logits
    acial
    -1.69
    roleum
    -1.56
    aten
    -1.54
    its
    -1.49
    asing
    -1.46
    illing
    -1.45
    abolism
    -1.44
    claiming
    -1.44
    acet
    -1.42
    itian
    -1.40
    POSITIVE LOGITS
    haus
    1.99
    enstein
    1.76
    ery
    1.59
    hower
    1.57
    tons
    1.56
     apparatus
    1.53
    iom
    1.52
    holm
    1.50
    ctl
    1.50
    forge
    1.49
    Activations Density 0.013%

    No Known Activations