© 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. 2-MLP-SM
    11. 23537
    Prev
    Next
    INDEX
    Explanations

    terms related to evaluating, assessing, and measuring various studies and outcomes

    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/2-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.2.hook_mlp_out
    Hook Layer
    2
    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
    405
    +0.13
    0.7%
    274
    +0.12
    0.7%
    98
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    219
    +0.13
    0.04
    406
    +0.12
    0.04
    404
    +0.11
    0.04
    Negative Logits
    cient
    -1.57
    ational
    -1.54
    ad
    -1.43
    langle
    -1.40
    acial
    -1.39
    gni
    -1.36
    ivities
    -1.34
    inine
    -1.33
    ys
    -1.31
    -[
    -1.30
    POSITIVE LOGITS
    ↵ ↵
    1.54
    Category
    1.49
     @@
    1.45
    =”
    1.45
    .
    1.41
    enez
    1.38
    aggio
    1.38
     transduction
    1.37
     possession
    1.35
    "}](#
    1.35
    Activations Density 0.109%

    No Known Activations