© 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 EvalsExportsinterp-engineNEWAPI 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. 26513
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "some."

    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
    10
    +0.14
    0.8%
    145
    +0.14
    0.8%
    242
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    308
    +0.14
    0.07
    213
    +0.14
    0.07
    402
    +0.11
    0.07
    Negative Logits
     centre
    -1.54
    oured
    -1.49
    ouse
    -1.47
     bin
    -1.45
     posterior
    -1.43
    js
    -1.40
    ingale
    -1.40
     fain
    -1.38
    uristic
    -1.38
     ball
    -1.37
    POSITIVE LOGITS
    ahan
    1.74
     Statutes
    1.49
    olini
    1.47
    erals
    1.44
    ¥
    1.43
    eral
    1.42
    enburg
    1.42
    ı
    1.39
    stage
    1.38
    ""
    1.37
    Activations Density 0.081%

    No Known Activations