© 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. 2-MLP-SM
    11. 26764
    Prev
    Next
    INDEX
    Explanations

    questions and inquiries about information or understanding

    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/2-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.2.hook_mlp_out
    Hook Layer
    2
    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
    308
    +0.12
    0.6%
    470
    +0.12
    0.6%
    33
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    380
    +0.12
    0.04
    470
    +0.12
    0.05
    33
    +0.11
    0.04
    Negative Logits
    adoc
    -1.70
     touch
    -1.52
     contrast
    -1.50
     scratch
    -1.45
     well
    -1.45
     DISCLAIM
    -1.43
     slap
    -1.43
     addition
    -1.42
     true
    -1.42
    yc
    -1.39
    POSITIVE LOGITS
    ender
    1.75
    documentclass
    1.75
    Company
    1.62
    Method
    1.57
    Mapping
    1.53
    isel
    1.47
    encer
    1.47
     agent
    1.47
    £
    1.47
    City
    1.45
    Activations Density 0.274%

    No Known Activations