© 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. 25545
    Prev
    Next
    INDEX
    Explanations

    phrases related to music and entertainment industry success

    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
    139
    +0.14
    0.8%
    412
    +0.13
    0.7%
    303
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    203
    +0.14
    0.36
    23
    +0.13
    0.31
    494
    +0.12
    0.25
    Negative Logits
    ĸ
    -2.95
    Ģ
    -2.57
    Ĭ
    -2.53
    ĵ
    -2.40
    ĻĤ
    -2.39
    ¯
    -2.34
    Ń
    -2.21
    ħ
    -2.19
    Ī
    -2.15
    Ĥ
    -2.12
    POSITIVE LOGITS
     budget
    1.60
    otal
    1.42
    matically
    1.40
    abase
    1.37
     his
    1.36
    idth
    1.35
    ivot
    1.35
    screen
    1.34
     director
    1.33
     Page
    1.33
    Activations Density 3.067%

    No Known Activations