© 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. 29186
    Prev
    Next
    INDEX
    Explanations

    closing curly braces in code snippets

    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
    258
    +0.19
    1.1%
    302
    +0.12
    0.7%
    217
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    302
    +0.19
    0.09
    258
    +0.12
    0.08
    435
    +0.11
    0.09
    Negative Logits
    ±
    -3.76
    ↵
    -3.64
    ↵
    -3.64
    ↵↵
    -3.64
    ↵↵
    -3.64
    -3.64
    -3.64
    -3.64
    ↵
    -3.64
    ↵    ↵
    -3.64
    POSITIVE LOGITS
    ctrine
    1.73
    ness
    1.44
     succession
    1.43
    iary
    1.39
    ',
    1.37
    bbe
    1.36
    android
    1.34
    ises
    1.34
    ”,
    1.34
    catch
    1.30
    Activations Density 0.137%

    No Known Activations