© 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. 30149
    Prev
    Next
    INDEX
    Explanations

    the word "as" used in various contexts

    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
    134
    +0.13
    0.7%
    329
    +0.13
    0.7%
    25
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    424
    +0.13
    0.17
    502
    +0.13
    0.15
    479
    +0.12
    0.15
    Negative Logits
    ruptcy
    -1.81
    fare
    -1.74
    writer
    -1.68
    cer
    -1.64
    freak
    -1.60
    stein
    -1.55
    __.
    -1.46
    batim
    -1.45
    fault
    -1.45
    ilogy
    -1.44
    POSITIVE LOGITS
    ĸ´
    3.63
    ı
    3.51
    ¨
    3.46
    Ľ
    3.44
    ¢
    3.33
    ľ
    3.33
    ¿½
    3.27
    Īĺ
    3.19
    ŀ
    3.16
    ĥ
    3.14
    Activations Density 0.338%

    No Known Activations