© 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. 26026
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "painted" and its variations in the text

    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
    376
    +0.18
    1.0%
    148
    +0.15
    0.8%
    156
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2
    +0.18
    0.01
    333
    +0.15
    0.01
    372
    +0.14
    0.01
    Negative Logits
     bre
    -1.47
    *>
    -1.47
    omorphisms
    -1.44
    ples
    -1.42
     cref
    -1.41
     gente
    -1.39
     href
    -1.38
     seu
    -1.37
    uten
    -1.35
     largest
    -1.35
    POSITIVE LOGITS
    otal
    2.10
    ¾
    1.83
    oon
    1.78
    ĻĤ
    1.77
    IFIC
    1.55
    ¸
    1.53
    tagged
    1.50
    FLAG
    1.46
    opan
    1.45
    ilent
    1.45
    Activations Density 0.011%

    No Known Activations