© 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. 29590
    Prev
    Next
    INDEX
    Explanations

    repeated references to years

    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
    364
    +0.12
    0.7%
    223
    +0.11
    0.6%
    197
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    223
    +0.12
    0.04
    364
    +0.11
    0.04
    212
    +0.10
    0.03
    Negative Logits
    ĨĴ
    -1.91
    Ĵ
    -1.79
    UST
    -1.72
     moderator
    -1.56
     Parenthood
    -1.50
    idem
    -1.48
     Respondents
    -1.41
     appellants
    -1.40
     Poor
    -1.40
     Channel
    -1.40
    POSITIVE LOGITS
    craft
    2.18
    book
    2.06
    nement
    2.06
    nel
    2.01
    books
    1.82
    sheet
    1.80
    ning
    1.79
    notes
    1.78
    "}](#
    1.70
    ned
    1.69
    Activations Density 0.089%

    No Known Activations