© 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. 27972
    Prev
    Next
    INDEX
    Explanations

    mentions of currency identifiers or financial terms

    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
    177
    +0.15
    0.8%
    143
    +0.12
    0.7%
    356
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    429
    +0.15
    0.01
    134
    +0.12
    0.01
    189
    +0.12
    0.01
    Negative Logits
    Īĺ
    -2.37
    į
    -2.27
    ĥ½
    -2.20
    Ĥ¬
    -2.19
    ³
    -2.17
    Ĥ
    -2.10
    ¬
    -2.06
    »
    -2.05
    ·¸
    -1.89
    Ĺ
    -1.87
    POSITIVE LOGITS
    ium
    2.06
    etto
    1.97
    PG
    1.78
    ieux
    1.69
    ENCE
    1.69
    ulent
    1.67
    ema
    1.66
    ional
    1.61
    oplasty
    1.56
    idable
    1.55
    Activations Density 0.012%

    No Known Activations