© 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. 30608
    Prev
    Next
    INDEX
    Explanations

    references to significant events or actions within a narrative context

    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
    100
    +0.13
    0.7%
    502
    +0.11
    0.7%
    510
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    170
    +0.13
    0.02
    510
    +0.11
    0.02
    343
    +0.11
    0.01
    Negative Logits
    §
    -2.02
    ³
    -2.01
    ĥ½
    -1.79
    ĥ
    -1.76
    ĵ
    -1.76
     \%
    -1.73
    į
    -1.70
    ľĵ
    -1.69
     '</
    -1.67
    Ĭ
    -1.67
    POSITIVE LOGITS
    ément
    1.73
    orphism
    1.66
    ography
    1.60
    nic
    1.58
    inson
    1.56
    piece
    1.53
    iliar
    1.51
    wise
    1.49
    het
    1.48
    finder
    1.48
    Activations Density 0.018%

    No Known Activations