© 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. 27053
    Prev
    Next
    INDEX
    Explanations

    topics related to the music industry and artist contracts

    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
    165
    +0.15
    0.9%
    258
    +0.14
    0.8%
    314
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    116
    +0.15
    0.01
    165
    +0.14
    0.01
    314
    +0.13
    0.01
    Negative Logits
    ĥ
    -2.59
    Ħ
    -2.46
    ħ
    -2.46
    İ
    -2.45
    ·¸
    -2.33
    ĥ½
    -2.33
    Ł
    -2.26
    ĨĴ
    -2.25
    ↵
    -2.24
    ↵    ↵
    -2.24
    POSITIVE LOGITS
     footsteps
    1.64
    via
    1.51
    leftrightarrow
    1.46
    angled
    1.45
     Latino
    1.43
    anged
    1.40
     sexuality
    1.39
     flowed
    1.34
     taste
    1.33
     pussy
    1.30
    Activations Density 0.039%

    No Known Activations