© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 27985
    Prev
    Next
    INDEX
    Explanations

    references to scaling or resizing processes

    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
    +0.18
    1.0%
    444
    +0.13
    0.8%
    376
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    444
    +0.18
    0.01
    162
    +0.13
    0.01
    19
    +0.13
    0.01
    Negative Logits
    aliana
    -1.56
     indeed
    -1.50
     attracted
    -1.48
     competed
    -1.48
    aking
    -1.47
    akov
    -1.47
    omorphisms
    -1.45
     cru
    -1.43
    urs
    -1.43
     hosted
    -1.41
    POSITIVE LOGITS
    ĻĤ
    1.93
    ¢
    1.87
    uple
    1.86
    ł
    1.81
    ¡
    1.72
    blr
    1.69
    Īĺ
    1.68
    Ļª
    1.66
    ¤
    1.64
    »¿
    1.64
    Activations Density 0.013%

    No Known Activations