© 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. 25420
    Prev
    Next
    INDEX
    Explanations

    punctuated dialogue or quotations within the text

    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
    235
    +0.14
    0.8%
    382
    +0.14
    0.7%
    105
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    235
    +0.14
    0.08
    225
    +0.14
    0.06
    18
    +0.12
    0.04
    Negative Logits
    imes
    -1.68
     vein
    -1.56
    ctions
    -1.47
     cents
    -1.43
    xmm
    -1.38
    alla
    -1.35
    ements
    -1.34
    öl
    -1.33
    ava
    -1.32
    hearted
    -1.32
    POSITIVE LOGITS
    ://
    1.50
     manually
    1.42
    inson
    1.40
     polling
    1.40
     signaled
    1.39
     {@
    1.38
    otyping
    1.38
     dock
    1.38
     bootstrap
    1.33
     Netanyahu
    1.31
    Activations Density 0.190%

    No Known Activations