© 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 EvalsExportsAPI 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. 25018
    Prev
    Next
    INDEX
    Explanations

    words related to musical ensembles and performance

    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
    341
    +0.12
    0.7%
    84
    +0.12
    0.7%
    302
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.12
    0.03
    302
    +0.12
    0.09
    100
    +0.12
    0.09
    Negative Logits
     centre
    -1.76
    ģ
    -1.68
    º
    -1.60
     \'
    -1.52
     longer
    -1.51
    ħ
    -1.47
    course
    -1.43
     RT
    -1.42
     GC
    -1.41
    £
    -1.40
    POSITIVE LOGITS
    hele
    1.48
    áĢ¯
    1.43
    wn
    1.42
     pleading
    1.41
    áŁ
    1.39
    felt
    1.39
    acity
    1.38
    athing
    1.35
    reens
    1.34
    čč
    1.34
    Activations Density 1.627%

    No Known Activations