© 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. 27660
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "were."

    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
    361
    +0.14
    0.8%
    345
    +0.13
    0.7%
    481
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    304
    +0.14
    0.09
    32
    +0.13
    0.07
    351
    +0.12
    0.07
    Negative Logits
    ĥ½
    -2.00
     Caption
    -1.75
    ²
    -1.73
    gs
    -1.64
    ¹
    -1.63
     hers
    -1.53
     labels
    -1.50
    ¿½
    -1.46
    wear
    -1.41
    ¥
    -1.38
    POSITIVE LOGITS
    eer
    1.60
    cht
    1.58
    afen
    1.54
    ophe
    1.53
    isco
    1.53
    aul
    1.52
    FPar
    1.48
    riton
    1.40
    olin
    1.40
    opan
    1.39
    Activations Density 0.108%

    No Known Activations