© 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. 29524
    Prev
    Next
    INDEX
    Explanations

    elements and attributes related to programming tools 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
    165
    +0.13
    0.7%
    71
    +0.13
    0.7%
    83
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    83
    +0.13
    0.02
    111
    +0.13
    0.02
    484
    +0.13
    0.02
    Negative Logits
    ¿
    -2.19
    s
    -1.74
    las
    -1.60
    ship
    -1.56
    ties
    -1.54
    lish
    -1.51
    sm
    -1.48
    go
    -1.43
    gments
    -1.40
     travelers
    -1.40
    POSITIVE LOGITS
    YPT
    1.72
    usalem
    1.57
    ieurs
    1.55
    blockList
    1.55
    //!
    1.52
    feb
    1.50
    /@
    1.49
    uable
    1.46
    llll
    1.46
    "}](#
    1.44
    Activations Density 0.046%

    No Known Activations