© 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 EvalsExportsAPI 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. 28990
    Prev
    Next
    INDEX
    Explanations

    scientific or observational phenomena

    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
    +0.35
    2.1%
    376
    +0.13
    0.8%
    365
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    156
    +0.35
    0.01
    365
    +0.13
    0.01
    453
    +0.11
    0.01
    Negative Logits
    ¸
    -2.32
    ¼
    -2.25
    ĥ½
    -2.16
     ↵
    -2.14
    č↵
    -2.14
    <|outofrange|>
    -2.14
    ↵
    -2.14
    <|outofrange|>
    -2.14
    -2.14
    čč
    -2.14
    POSITIVE LOGITS
    ical
    1.93
    icle
    1.75
    ics
    1.72
    emis
    1.65
    ional
    1.59
    hell
    1.59
    ica
    1.58
    arily
    1.53
    iary
    1.51
    isms
    1.51
    Activations Density 0.015%

    No Known Activations