© 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. 30109
    Prev
    Next
    INDEX
    Explanations

    instances of the word "singing" and its variations

    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
    156
    +0.24
    1.4%
    376
    +0.16
    0.9%
    329
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    26
    +0.24
    0.02
    329
    +0.16
    0.02
    292
    +0.12
    0.01
    Negative Logits
    apine
    -1.75
    ––––––––
    -1.46
     Publ
    -1.45
    idegger
    -1.42
    č↵č↵
    -1.39
    MSO
    -1.39
    ---|---
    -1.36
     Athletics
    -1.33
    WIDTH
    -1.33
    TRODUCTION
    -1.30
    POSITIVE LOGITS
    bird
    1.97
    Ĵ
    1.83
    apore
    1.75
    birds
    1.65
    ¥
    1.65
    ª
    1.62
    along
    1.62
    craft
    1.58
    ¿
    1.57
    bial
    1.47
    Activations Density 0.569%

    No Known Activations