© 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. 2-MLP-SM
    11. 25906
    Prev
    Next
    INDEX
    Explanations

    tags related to HTML

    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
    23
    +0.14
    0.8%
    156
    +0.13
    0.7%
    87
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    414
    +0.14
    0.01
    339
    +0.13
    0.03
    8
    +0.10
    0.03
    Negative Logits
    wordpress
    -1.87
     archives
    -1.83
    ¬
    -1.75
    blogger
    -1.66
    º
    -1.61
    »¿
    -1.61
    ¾
    -1.59
    ictionaries
    -1.59
    ®
    -1.55
     archive
    -1.54
    POSITIVE LOGITS
    oused
    1.53
    rolling
    1.45
     Gren
    1.44
    ]:
    1.41
    bbing
    1.38
     depend
    1.38
     Teams
    1.37
     see
    1.37
     ..."
    1.36
     whichever
    1.36
    Activations Density 0.089%

    No Known Activations