© 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. 26003
    Prev
    Next
    INDEX
    Explanations

    terms related to printing and document formatting

    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
    386
    +0.13
    0.7%
    301
    +0.12
    0.7%
    48
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    429
    +0.13
    0.04
    301
    +0.12
    0.04
    410
    +0.12
    0.03
    Negative Logits
    Ń
    -2.19
    Īĺ
    -2.17
    ĥ½
    -2.08
    ·¸
    -2.07
    «
    -2.05
    ¬
    -1.97
    ¹
    -1.91
    ¿½
    -1.90
    ĸ´
    -1.90
    ĭ
    -1.83
    POSITIVE LOGITS
    develop
    1.68
    lap
    1.56
    lay
    1.52
    corp
    1.51
    degree
    1.48
    abine
    1.46
    mand
    1.43
    substantial
    1.42
    ATH
    1.41
    fall
    1.41
    Activations Density 0.080%

    No Known Activations