© 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. 29253
    Prev
    Next
    INDEX
    Explanations

    the presence of specific time-related phrases or dates

    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
    203
    +0.17
    1.0%
    369
    +0.14
    0.8%
    51
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    31
    +0.17
    0.01
    209
    +0.14
    0.01
    203
    +0.12
    0.01
    Negative Logits
     midst
    -1.86
     slavery
    -1.59
     presence
    -1.52
     pity
    -1.45
     full
    -1.44
     close
    -1.42
     nobody
    -1.41
    ching
    -1.41
     logarithm
    -1.39
     commerce
    -1.38
    POSITIVE LOGITS
    ¾
    3.41
    ĥ½
    3.29
    ļ
    3.22
    ³
    3.14
    ħ
    3.03
    ĭ
    3.02
    ¶
    3.01
    ª
    3.00
    µ
    2.99
    ±
    2.96
    Activations Density 0.009%

    No Known Activations