© 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. 30711
    Prev
    Next
    INDEX
    Explanations

    usage of the term "macro" in various contexts

    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
    +0.14
    0.8%
    275
    +0.13
    0.7%
    463
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    275
    +0.14
    0.01
    463
    +0.13
    0.01
    172
    +0.12
    0.01
    Negative Logits
    unnumbered
    -1.58
    ÑĶ
    -1.45
    ureus
    -1.41
     Promise
    -1.41
    ockey
    -1.40
    ighting
    -1.40
    rapy
    -1.38
    rosis
    -1.37
    REAM
    -1.34
    omitempty
    -1.34
    POSITIVE LOGITS
    cles
    2.02
    cyclic
    1.97
    cad
    1.78
    quart
    1.77
    plots
    1.69
    ULAR
    1.68
    processor
    1.67
    bial
    1.67
    icals
    1.64
    calc
    1.63
    Activations Density 0.013%

    No Known Activations