© 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. 28931
    Prev
    Next
    INDEX
    Explanations

    references to biological conditions or observations related to cellular 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
    156
    +0.24
    1.4%
    467
    +0.14
    0.8%
    362
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    487
    +0.24
    0.01
    123
    +0.14
    0.01
    385
    +0.13
    0.01
    Negative Logits
    ween
    -1.80
    akin
    -1.62
    ighter
    -1.51
    agn
    -1.49
    agle
    -1.49
    uen
    -1.48
    chanical
    -1.45
    unt
    -1.44
    ashi
    -1.44
    itian
    -1.41
    POSITIVE LOGITS
    ¿½
    3.01
    Ł
    2.91
    ĻĤ
    2.75
    ¡
    2.73
    ŀ
    2.70
    Ģ
    2.62
    º
    2.59
    ĺ
    2.54
    ®
    2.47
    ¢
    2.45
    Activations Density 0.120%

    No Known Activations