© 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. 25904
    Prev
    Next
    INDEX
    Explanations

    references to grid structures or terminology in technical contexts

    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
    +0.16
    0.9%
    141
    +0.14
    0.8%
    156
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    141
    +0.16
    0.01
    243
    +0.14
    0.00
    460
    +0.13
    0.00
    Negative Logits
    ĥ
    -1.93
    Ģ
    -1.66
    uses
    -1.56
    ĵ
    -1.55
    rogens
    -1.50
    omers
    -1.50
     slightest
    -1.49
     same
    -1.48
    Ĩ
    -1.48
    ¯
    -1.47
    POSITIVE LOGITS
    iron
    2.25
    istry
    2.01
    face
    1.88
    plit
    1.85
    ulator
    1.78
    burn
    1.74
    pool
    1.74
    legged
    1.71
    bank
    1.71
    shock
    1.69
    Activations Density 0.004%

    No Known Activations