© 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
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 0-MLP-SM
    6. 26963
    Prev
    Next
    INDEX
    Explanations

    types of expressions and declarations in programming code

    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
    +0.22
    1.2%
    301
    +0.15
    0.9%
    392
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    301
    +0.22
    0.02
    392
    +0.15
    0.01
    217
    +0.11
    0.01
    Negative Logits
    ĥ½
    -4.69
    ¬
    -4.27
    ½
    -4.21
    ¸
    -4.10
    ·¸
    -4.06
    Ń
    -4.06
    ´
    -4.04
    ľĵ
    -3.96
    Ĭ
    -3.93
    ı
    -3.85
    POSITIVE LOGITS
    smen
    1.64
    istic
    1.60
    nikov
    1.52
    Handler
    1.47
    wise
    1.46
    ally
    1.46
    injection
    1.46
    al
    1.45
    builder
    1.43
    naire
    1.41
    Activations Density 0.026%

    No Known Activations