© 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. 24024
    Prev
    Next
    INDEX
    Explanations

    conjunctions and phrases indicating contrast or exception

    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
    505
    +0.12
    0.6%
    147
    +0.11
    0.6%
    487
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    147
    +0.12
    0.08
    274
    +0.11
    0.09
    266
    +0.11
    0.01
    Negative Logits
    $$
    -1.56
    Ļª
    -1.39
     various
    -1.38
    -1.32
    pshire
    -1.28
    ³³³³³³³³
    -1.26
     later
    -1.25
    awning
    -1.20
    ++;
    -1.19
    latest
    -1.18
    POSITIVE LOGITS
     anymore
    1.76
     alone
    1.64
    ugu
    1.51
    fiction
    1.47
     nor
    1.46
     itself
    1.45
    bare
    1.43
    isse
    1.41
    izen
    1.41
    ifies
    1.39
    Activations Density 1.336%

    No Known Activations