© 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. 23576
    Prev
    Next
    INDEX
    Explanations

    elements and attributes related to structured data in documents

    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
    23
    +0.14
    0.8%
    198
    +0.14
    0.8%
    90
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    198
    +0.14
    0.02
    341
    +0.14
    0.02
    478
    +0.12
    0.02
    Negative Logits
    '):
    -1.91
    ’,
    -1.77
    )?
    -1.65
     peric
    -1.63
     tbsp
    -1.53
    ’.
    -1.53
    ém
    -1.50
    urname
    -1.48
    blic
    -1.42
     pertains
    -1.42
    POSITIVE LOGITS
    better
    1.77
    further
    1.62
     customers
    1.54
    Plaintiffs
    1.49
     plaintiffs
    1.42
    oper
    1.40
    avery
    1.36
    yer
    1.36
    ricks
    1.36
    OMA
    1.35
    Activations Density 0.151%

    No Known Activations