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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 28486
    Prev
    Next
    INDEX
    Explanations

    instances of the pronoun "it."

    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
    433
    +0.13
    0.7%
    430
    +0.12
    0.7%
    78
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    352
    +0.13
    0.22
    185
    +0.12
    0.18
    165
    +0.11
    0.17
    Negative Logits
    shire
    -1.71
    ”,
    -1.50
     Lithuan
    -1.45
     Polish
    -1.44
    uality
    -1.41
     fertility
    -1.38
    entially
    -1.34
    isson
    -1.31
    holder
    -1.30
     councill
    -1.28
    POSITIVE LOGITS
    heed
    1.69
    hin
    1.64
     Atty
    1.57
    rico
    1.47
    rout
    1.45
    ]>
    1.44
     drives
    1.41
    zia
    1.40
    books
    1.40
    Books
    1.40
    Activations Density 0.395%

    No Known Activations