© 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. 0-MLP-SM
    11. 25727
    Prev
    Next
    INDEX
    Explanations

    transitive verbs related to urgency or necessity

    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
    355
    +0.13
    0.7%
    219
    +0.11
    0.6%
    282
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    69
    +0.13
    0.28
    434
    +0.11
    0.18
    98
    +0.11
    0.08
    Negative Logits
     proceeds
    -1.53
     proceedings
    -1.47
    aurus
    -1.44
    bler
    -1.44
     Reviews
    -1.39
    âĢŁ
    -1.37
     recently
    -1.35
    ergic
    -1.35
    olated
    -1.34
     indicator
    -1.33
    POSITIVE LOGITS
    ¥
    3.63
    µ
    3.58
    ¶
    3.50
    ·
    3.46
    Ĥ¬
    3.45
    Īĺ
    3.41
    Ĺ
    3.27
    §
    3.26
    ľ
    3.23
    ±
    3.23
    Activations Density 1.877%

    No Known Activations