© 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. 26472
    Prev
    Next
    INDEX
    Explanations

    terms related to digital marketing or management systems

    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
    356
    +0.11
    0.7%
    304
    +0.10
    0.6%
    214
    +0.09
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    159
    +0.11
    0.01
    420
    +0.10
    0.01
    356
    +0.09
    0.01
    Negative Logits
    Īĺ
    -2.66
    ¿½
    -2.53
    Ĺ
    -2.20
    ·¸
    -2.10
    ĥ
    -2.10
    ĸ´
    -2.05
    µ
    -2.05
    ĥ½
    -2.04
     answered
    -1.96
    ķ
    -1.94
    POSITIVE LOGITS
    :`
    1.95
    ART
    1.87
    ETHOD
    1.83
     (“
    1.76
    ieu
    1.76
    net
    1.74
    ieux
    1.73
    arts
    1.67
    ,[
    1.65
    asset
    1.62
    Activations Density 0.010%

    No Known Activations