© 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 EvalsExportsinterp-engineNEWAPI 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. 23978
    Prev
    Next
    INDEX
    Explanations

    phrases and statements about things that are perceived as interesting or noteworthy

    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
    47
    +0.12
    0.7%
    370
    +0.11
    0.6%
    154
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    277
    +0.12
    0.09
    424
    +0.11
    0.03
    155
    +0.11
    0.10
    Negative Logits
    chez
    -1.59
     experiments
    -1.35
     thro
    -1.33
     sequenced
    -1.30
    alone
    -1.28
     patented
    -1.25
     upstairs
    -1.25
     features
    -1.25
     tons
    -1.24
     doc
    -1.23
    POSITIVE LOGITS
     False
    1.65
    /.
    1.52
    imer
    1.50
    âģĦ
    1.47
    hang
    1.43
    FONT
    1.40
    #'
    1.36
     curvature
    1.32
     background
    1.31
    DEF
    1.30
    Activations Density 1.883%

    No Known Activations