© 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. 29953
    Prev
    Next
    INDEX
    Explanations

    references to relationships or relational structures

    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
    0.9%
    348
    +0.12
    0.7%
    320
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    320
    +0.15
    0.02
    264
    +0.12
    0.02
    232
    +0.12
    0.02
    Negative Logits
    ·¸
    -3.11
    Ĥ
    -3.03
    Ĺ
    -2.94
    »¿
    -2.92
    ľ
    -2.92
    ¿
    -2.90
    Ħ
    -2.90
    ¾
    -2.87
    Ĥ¬
    -2.81
    Ĭ
    -2.79
    POSITIVE LOGITS
    ató
    2.38
    forge
    2.09
    thouse
    1.84
    entin
    1.68
    bench
    1.64
    issue
    1.62
    bard
    1.61
    igi
    1.59
    charts
    1.57
    kok
    1.56
    Activations Density 0.018%

    No Known Activations