© 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. 26018
    Prev
    Next
    INDEX
    Explanations

    names or references related to the term "Gwyn."

    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
    +0.13
    0.7%
    466
    +0.12
    0.7%
    429
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.13
    0.01
    200
    +0.12
    0.01
    370
    +0.11
    0.01
    Negative Logits
     present
    -1.64
     corresponding
    -1.63
    ?”
    -1.62
    ?",
    -1.61
    ricular
    -1.56
     beneficial
    -1.54
    hes
    -1.51
     detrimental
    -1.48
     long
    -1.44
     correl
    -1.43
    POSITIVE LOGITS
    ĻĤ
    2.56
    º
    2.30
    ĸ
    2.14
    ¢
    2.12
    headed
    2.06
    ¬
    1.98
    §
    1.93
    £
    1.93
    Ł
    1.86
    ¶
    1.82
    Activations Density 0.019%

    No Known Activations