© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 27842
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific or technical discussions

    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
    +0.19
    1.1%
    156
    +0.18
    1.0%
    52
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    257
    +0.19
    0.01
    408
    +0.18
    0.01
    404
    +0.12
    0.01
    Negative Logits
    eker
    -1.57
    ansen
    -1.56
     explicitly
    -1.51
    kowski
    -1.51
    ressed
    -1.49
    enger
    -1.49
    anner
    -1.47
    aler
    -1.41
    arb
    -1.41
    omycin
    -1.40
    POSITIVE LOGITS
     DAMAGE
    1.59
    "}](#
    1.57
     speaking
    1.49
    pires
    1.35
    None
    1.32
    death
    1.30
    idades
    1.29
     Aid
    1.25
     reproduce
    1.23
     divid
    1.23
    Activations Density 0.009%

    No Known Activations