© 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. 23631
    Prev
    Next
    INDEX
    Explanations

    questions that start with the word "Which."

    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
    98
    +0.14
    0.7%
    182
    +0.12
    0.6%
    462
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    182
    +0.14
    0.03
    300
    +0.12
    0.01
    406
    +0.11
    0.02
    Negative Logits
    ĨĴ
    -2.92
    ¿½
    -2.87
       ↵
    -2.83
    č↵
    -2.82
    -2.82
    ↵
    -2.82
    ↵
    -2.82
    ↵
    -2.82
    ↵
    -2.82
    ↵
    -2.82
    POSITIVE LOGITS
    SRC
    1.82
    cript
    1.73
    MENT
    1.64
    emia
    1.60
    osome
    1.60
    lickr
    1.59
    media
    1.58
    LIBR
    1.58
    osomes
    1.56
    HTML
    1.55
    Activations Density 0.316%

    No Known Activations