© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 27671
    Prev
    Next
    INDEX
    Explanations

    references to continental concepts or settings

    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
    362
    +0.17
    1.0%
    156
    +0.14
    0.8%
    444
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.17
    0.01
    429
    +0.14
    0.01
    180
    +0.14
    0.01
    Negative Logits
    ellow
    -1.55
    ted
    -1.50
     tear
    -1.47
    inous
    -1.46
     nearly
    -1.44
     promise
    -1.41
     ?>
    -1.37
    tons
    -1.36
    -)
    -1.34
    oped
    -1.33
    POSITIVE LOGITS
    Īĺ
    2.74
    ©
    2.73
    µ
    2.63
    ¡
    2.61
    ´
    2.60
    »¿
    2.60
    ł
    2.50
    ·¸
    2.42
    £
    2.37
    »
    2.37
    Activations Density 0.027%

    No Known Activations