© 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. 29580
    Prev
    Next
    INDEX
    Explanations

    words related to advocacy and support for various causes

    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
    376
    +0.18
    1.0%
    472
    +0.12
    0.7%
    95
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    472
    +0.18
    0.02
    365
    +0.12
    0.01
    95
    +0.12
    0.01
    Negative Logits
     Partnership
    -1.84
    shore
    -1.65
     Share
    -1.49
    Posted
    -1.49
     Census
    -1.46
    UB
    -1.45
    Story
    -1.42
    oti
    -1.39
     preponderance
    -1.36
    Job
    -1.34
    POSITIVE LOGITS
    iol
    1.89
    gery
    1.88
    amma
    1.68
     crus
    1.67
    agment
    1.64
    ship
    1.60
    doms
    1.58
    -[
    1.54
    ppo
    1.52
    hdr
    1.50
    Activations Density 0.020%

    No Known Activations