© 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. 27873
    Prev
    Next
    INDEX
    Explanations

    words related to tracking or following

    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
    38
    +0.14
    0.8%
    376
    +0.12
    0.7%
    246
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    80
    +0.14
    0.01
    38
    +0.12
    0.01
    138
    +0.11
    0.01
    Negative Logits
    Ļª
    -4.20
    ¯
    -4.15
    Ĩ
    -4.07
    µ
    -4.01
    ı
    -3.97
    ĭ
    -3.84
    Ĥ¬
    -3.83
    Ĺ
    -3.81
    ĨĴ
    -3.79
    Ħ
    -3.78
    POSITIVE LOGITS
    pieces
    1.90
    back
    1.89
    igraphy
    1.86
    backs
    1.83
    ball
    1.81
    balls
    1.81
    shots
    1.80
    amycin
    1.70
    able
    1.68
    church
    1.68
    Activations Density 0.013%

    No Known Activations