© 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. 30095
    Prev
    Next
    INDEX
    Explanations

    the occurrence of the word "Is."

    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
    +0.15
    0.8%
    81
    +0.14
    0.8%
    337
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    337
    +0.15
    0.03
    259
    +0.14
    0.03
    81
    +0.13
    0.03
    Negative Logits
    »
    -2.10
    ©
    -1.99
    ¦
    -1.97
    ł
    -1.93
    Ĵ
    -1.92
    Ľ
    -1.89
    ´
    -1.83
    ģ
    -1.81
    ľ
    -1.80
    ĥ½
    -1.76
    POSITIVE LOGITS
    olated
    1.81
    ocyan
    1.79
    documentclass
    1.63
    olation
    1.53
    idia
    1.52
    omnia
    1.48
    ederal
    1.45
    ol
    1.43
    ruptcy
    1.41
     Legisl
    1.39
    Activations Density 2.104%

    No Known Activations