© 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. 23158
    Prev
    Next
    INDEX
    Explanations

    programming code snippets and syntax elements

    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
    153
    +0.13
    0.7%
    175
    +0.12
    0.7%
    52
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    489
    +0.13
    0.01
    421
    +0.12
    0.02
    376
    +0.10
    0.02
    Negative Logits
    '"
    -1.60
     '</
    -1.54
    abulary
    -1.49
     '"
    -1.46
     _________
    -1.46
    romycin
    -1.45
    .'"
    -1.44
    abin
    -1.41
     ord
    -1.40
    oder
    -1.36
    POSITIVE LOGITS
    bourg
    1.75
    itals
    1.70
    iele
    1.56
     stadium
    1.48
    ]:
    1.46
    ockets
    1.40
    ]):
    1.39
     Arena
    1.39
    ascus
    1.38
    itarian
    1.38
    Activations Density 0.111%

    No Known Activations