© 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. 2-MLP-SM
    11. 23023
    Prev
    Next
    INDEX
    Explanations

    references to music, particularly in relation to artists, bands, and their works

    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
    23
    +0.18
    1.0%
    316
    +0.12
    0.6%
    329
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    316
    +0.18
    0.10
    151
    +0.12
    0.09
    23
    +0.11
    0.05
    Negative Logits
    blogger
    -1.98
    ='
    -1.68
    Television
    -1.66
    Voice
    -1.55
    Songs
    -1.54
    Library
    -1.53
    tone
    -1.52
     studio
    -1.52
     storyline
    -1.50
     audiences
    -1.49
    POSITIVE LOGITS
    Ĺ
    2.60
    ħ
    2.49
    ł
    2.43
    ±
    2.38
    »
    2.36
    ³
    2.29
    Ħ
    2.27
    ¤
    2.24
    µ
    2.15
    ķ
    2.14
    Activations Density 1.117%

    No Known Activations