© 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. 29054
    Prev
    Next
    INDEX
    Explanations

    the presence of the word "inc."

    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
    +0.17
    0.9%
    376
    +0.14
    0.7%
    148
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    490
    +0.17
    0.02
    245
    +0.14
    0.02
    486
    +0.12
    0.02
    Negative Logits
    eca
    -1.71
    ego
    -1.69
    ÅĽÄĩ
    -1.61
    ypse
    -1.40
     intentions
    -1.39
    ew
    -1.39
    ż
    -1.37
    tti
    -1.36
    hood
    -1.35
    ek
    -1.35
    POSITIVE LOGITS
    urious
    1.65
    orect
    1.63
    igator
    1.63
    ensed
    1.56
    identally
    1.56
    ubation
    1.47
     concluded
    1.46
     infring
    1.46
    igating
    1.43
    ugin
    1.41
    Activations Density 2.161%

    No Known Activations