© 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. 2-MLP-SM
    11. 25273
    Prev
    Next
    INDEX
    Explanations

    terms related to software development and programming 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
    156
    +0.20
    1.1%
    23
    +0.14
    0.8%
    475
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.20
    0.03
    374
    +0.14
    0.01
    475
    +0.13
    0.03
    Negative Logits
    ĨĴ
    -2.35
    ¹
    -2.31
    ¬
    -2.27
    Ľ
    -2.14
    ī
    -2.09
    -1.96
    -1.96
    ↵↵
    -1.96
    -1.96
    -1.96
    POSITIVE LOGITS
     following
    1.46
     volumes
    1.45
    ÑĤоÑĢ
    1.44
     extracts
    1.43
     chapters
    1.42
     mult
    1.40
     latter
    1.39
     regards
    1.39
     subt
    1.38
    words
    1.37
    Activations Density 0.757%

    No Known Activations