© 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. 26607
    Prev
    Next
    INDEX
    Explanations

    references to root objects in programming or data structures

    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
    156
    +0.19
    1.1%
    376
    +0.14
    0.8%
    285
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    285
    +0.19
    0.01
    248
    +0.14
    0.01
    78
    +0.13
    0.01
    Negative Logits
    ights
    -1.68
    ellow
    -1.47
     certain
    -1.46
    ?'
    -1.39
    aturing
    -1.38
    rypt
    -1.38
    opf
    -1.37
    itter
    -1.36
     otherwise
    -1.35
    usement
    -1.34
    POSITIVE LOGITS
    ¼
    1.85
    s
    1.78
    ĸ
    1.73
    ĻĤ
    1.73
    £
    1.61
    stown
    1.59
    yards
    1.58
    sis
    1.57
     ejemplo
    1.51
    sy
    1.48
    Activations Density 0.042%

    No Known Activations