© 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. 2-MLP-SM
    11. 23470
    Prev
    Next
    INDEX
    Explanations

    instances of the word "invitation" 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/2-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.2.hook_mlp_out
    Hook Layer
    2
    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
    483
    +0.17
    0.9%
    156
    +0.14
    0.8%
    102
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.17
    0.03
    171
    +0.14
    -0.01
    353
    +0.13
    0.05
    Negative Logits
    §
    -2.35
    »¿
    -2.33
    ĻĤ
    -2.32
    ĥ½
    -2.27
    ģ
    -2.26
    ¥
    -2.13
    ¢
    -2.11
    ±
    -2.10
    ¼
    -2.09
    Ĥ¬
    -2.05
    POSITIVE LOGITS
     worth
    1.56
     maintained
    1.54
     still
    1.50
    áĥĶ
    1.48
     soon
    1.47
    -->
    1.44
    points
    1.43
     centered
    1.39
     remain
    1.37
    à¯ģ
    1.35
    Activations Density 0.937%

    No Known Activations