© 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. 0-MLP-SM
    11. 30293
    Prev
    Next
    INDEX
    Explanations

    code snippets related to API interactions and configurations

    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/0-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.0.hook_mlp_out
    Hook Layer
    0
    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
    279
    +0.14
    0.7%
    247
    +0.13
    0.7%
    160
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    48
    +0.14
    0.12
    35
    +0.13
    0.10
    322
    +0.13
    0.10
    Negative Logits
    ptions
    -1.45
    opard
    -1.43
    amento
    -1.43
    anne
    -1.43
     sut
    -1.40
     corners
    -1.38
     Defendant
    -1.35
     penet
    -1.34
     DAPI
    -1.33
    chen
    -1.32
    POSITIVE LOGITS
    ired
    1.70
     team
    1.57
    gets
    1.52
    ...](
    1.52
    numeric
    1.50
    hs
    1.45
    IRED
    1.45
    usted
    1.41
    pires
    1.39
    WH
    1.37
    Activations Density 0.183%

    No Known Activations