© 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. 26393
    Prev
    Next
    INDEX
    Explanations

    phrases indicating functions or actions related to "to", often signifying intention or direction

    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
    272
    +0.11
    0.6%
    229
    +0.11
    0.6%
    241
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    69
    +0.11
    0.38
    151
    +0.11
    0.31
    434
    +0.10
    0.30
    Negative Logits
    ł
    -2.24
    ĻĤ
    -2.23
    catalina
    -1.94
    ľĵ
    -1.92
    googleapis
    -1.89
    º
    -1.81
    ĨĴ
    -1.69
    define
    -1.66
    ¼
    -1.62
    -1.60
    POSITIVE LOGITS
    pace
    1.42
    lords
    1.41
    ystems
    1.41
    ority
    1.39
    mates
    1.39
    lies
    1.34
     rivals
    1.32
    temporal
    1.30
    dimensional
    1.29
     GDP
    1.29
    Activations Density 1.767%

    No Known Activations