© 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
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 0-MLP-SM
    6. 25668
    Prev
    Next
    INDEX
    Explanations

    mentions of "central."

    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
    362
    +0.17
    1.0%
    30
    +0.14
    0.8%
    162
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    162
    +0.17
    0.01
    30
    +0.14
    0.01
    362
    +0.14
    0.01
    Negative Logits
    rian
    -1.71
     only
    -1.68
    matically
    -1.60
    LLOW
    -1.58
    omorphisms
    -1.56
    astern
    -1.52
    ellow
    -1.52
     anonymity
    -1.51
     usual
    -1.49
    acial
    -1.47
    POSITIVE LOGITS
    ¼
    2.74
    º
    2.63
    ¾
    2.16
    ¸
    2.13
    ¹
    2.03
    °
    2.00
    µ
    1.98
    ¬
    1.90
    £
    1.89
    ifornia
    1.84
    Activations Density 0.008%

    No Known Activations