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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 0-MLP-SM
    6. 28153
    Prev
    Next
    INDEX
    Explanations

    the term "aspiring" 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
    511
    +0.14
    0.8%
    148
    +0.13
    0.8%
    118
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    511
    +0.14
    0.01
    420
    +0.13
    0.01
    421
    +0.12
    0.01
    Negative Logits
    hip
    -1.95
     she
    -1.71
     entre
    -1.68
     idea
    -1.67
     else
    -1.53
     however
    -1.51
     entire
    -1.50
    aning
    -1.50
     notion
    -1.46
    hey
    -1.45
    POSITIVE LOGITS
    herical
    1.72
    ray
    1.72
    hole
    1.70
    fire
    1.68
    ensable
    1.58
    ureus
    1.50
    beam
    1.50
    ROM
    1.49
     (,
    1.48
    ouch
    1.47
    Activations Density 0.006%

    No Known Activations