© 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. 25336
    Prev
    Next
    INDEX
    Explanations

    instances of the term "vertical" in various 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
    156
    +0.21
    1.2%
    502
    +0.13
    0.8%
    508
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    502
    +0.21
    0.01
    508
    +0.13
    0.01
    287
    +0.11
    0.01
    Negative Logits
    chers
    -1.66
    rog
    -1.64
    rogen
    -1.50
    aves
    -1.49
     brutal
    -1.48
     horrific
    -1.45
     precious
    -1.45
    orters
    -1.44
     costly
    -1.43
    googleapis
    -1.43
    POSITIVE LOGITS
    ĺ
    3.11
    £
    3.02
    ¡
    3.01
    ĸ
    2.93
    Ł
    2.92
    ĻĤ
    2.83
    Īĺ
    2.73
    ĭ
    2.67
    ¬
    2.62
    ´
    2.58
    Activations Density 0.487%

    No Known Activations