© 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. 27661
    Prev
    Next
    INDEX
    Explanations

    parenthetical expressions

    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
    435
    +0.14
    0.8%
    335
    +0.11
    0.6%
    333
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    188
    +0.14
    0.24
    486
    +0.11
    0.16
    154
    +0.11
    0.15
    Negative Logits
    ¥
    -2.02
    §
    -1.96
    ¦
    -1.88
    IJ
    -1.88
    ¼
    -1.81
    į
    -1.76
    ¤
    -1.74
    Ń
    -1.72
    ļ
    -1.71
    ĵ
    -1.65
    POSITIVE LOGITS
    ionine
    1.71
    $^{-
    1.51
    tons
    1.51
    áĢ¯
    1.44
    ouston
    1.42
     persists
    1.40
    adian
    1.40
     survives
    1.39
    unreadable
    1.39
     epigen
    1.38
    Activations Density 0.349%

    No Known Activations