© 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
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. MLP Post
    9. 0-MLP-SM
    11. 27031
    Prev
    Next
    INDEX
    Explanations

    repeated mentions of a specific product or item

    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
    +0.16
    0.9%
    52
    +0.15
    0.9%
    286
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    52
    +0.16
    0.03
    286
    +0.15
    0.02
    465
    +0.13
    0.02
    Negative Logits
    Ļª
    -2.41
    Ĥ¬
    -2.30
    ¨
    -2.29
    Ĭ
    -2.27
    §
    -2.17
    ·¸
    -2.16
    Ĥ
    -2.16
    µ
    -2.15
    ±
    -2.10
    ¶
    -2.08
    POSITIVE LOGITS
    chaft
    1.85
    ional
    1.84
    ue
    1.76
    Bank
    1.74
    aurus
    1.73
    cript
    1.59
    ivist
    1.57
    heet
    1.56
    ista
    1.55
    counter
    1.55
    Activations Density 0.021%

    No Known Activations