© 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 EvalsExportsAPI 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. 28867
    Prev
    Next
    INDEX
    Explanations

    the phrase "after" indicating sequences of events or timings

    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
    376
    +0.19
    1.1%
    38
    +0.14
    0.8%
    266
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    266
    +0.19
    0.07
    38
    +0.14
    0.07
    4
    +0.13
    0.06
    Negative Logits
    adian
    -2.11
    uchy
    -2.02
    ICU
    -1.72
    Ī
    -1.63
    »¿
    -1.60
    ĩ
    -1.57
    UTH
    -1.57
    HS
    -1.56
    USB
    -1.53
    umpy
    -1.52
    POSITIVE LOGITS
    noon
    1.86
     accompl
    1.71
     heels
    1.50
    math
    1.49
     graduating
    1.48
    lessly
    1.48
     submitting
    1.46
     winning
    1.45
     saving
    1.45
     generation
    1.44
    Activations Density 0.074%

    No Known Activations