© 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. 2-MLP-SM
    11. 25535
    Prev
    Next
    INDEX
    Explanations

    references to betting or gambling concepts

    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/2-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.2.hook_mlp_out
    Hook Layer
    2
    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
    +0.18
    1.0%
    76
    +0.12
    0.7%
    332
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    332
    +0.18
    0.08
    448
    +0.12
    0.03
    23
    +0.12
    0.03
    Negative Logits
    ção
    -1.49
     obstacle
    -1.44
     vu
    -1.42
     loser
    -1.40
    iddle
    -1.37
     occasion
    -1.35
     forum
    -1.33
     happening
    -1.33
    ÃŃc
    -1.32
     \%
    -1.30
    POSITIVE LOGITS
    ŀ
    2.23
    ĸ
    2.22
    ģ
    2.20
    º
    2.19
    ĵ
    2.15
    ij
    2.14
    µ
    2.09
    Ŀ
    2.07
    ¸
    2.04
    ·
    2.03
    Activations Density 1.758%

    No Known Activations