© 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. 26849
    Prev
    Next
    INDEX
    Explanations

    references to cryptocurrency

    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
    +0.17
    1.0%
    376
    +0.12
    0.7%
    363
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    256
    +0.17
    0.01
    474
    +0.12
    0.01
    363
    +0.11
    0.01
    Negative Logits
     pronounced
    -1.58
     ]
    -1.54
     your
    -1.48
     gonna
    -1.43
     called
    -1.41
     gone
    -1.38
    Ĥ¬
    -1.37
     Subject
    -1.36
     canceled
    -1.36
     considered
    -1.35
    POSITIVE LOGITS
    eries
    2.07
    craft
    1.91
    -$\
    1.90
     minded
    1.85
    isms
    1.84
    cav
    1.82
    ÅĽci
    1.81
    istry
    1.77
    works
    1.75
    worthy
    1.75
    Activations Density 0.034%

    No Known Activations