© 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
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. MLP Post
    9. 0-MLP-SM
    11. 28057
    Prev
    Next
    INDEX
    Explanations

    phrases or context related to leaving or exiting

    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
    497
    +0.14
    0.8%
    479
    +0.11
    0.6%
    274
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    497
    +0.14
    0.12
    479
    +0.11
    0.11
    264
    +0.11
    0.08
    Negative Logits
    iger
    -1.64
    ather
    -1.56
    ;</
    -1.53
    GBT
    -1.53
     BGCOLOR
    -1.52
    rends
    -1.52
    itime
    -1.50
    ropical
    -1.48
    quo
    -1.47
    anyl
    -1.44
    POSITIVE LOGITS
    Ļª
    2.30
    lining
    2.21
    ermost
    2.17
    µ
    1.95
    ĻĤ
    1.91
    Ļ
    1.91
    IJ
    1.84
    ¸
    1.81
    perform
    1.81
    £
    1.78
    Activations Density 0.840%

    No Known Activations