© 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. 29660
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "analyze" 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/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
    59
    +0.17
    1.0%
    376
    +0.14
    0.8%
    412
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    59
    +0.17
    0.01
    412
    +0.14
    0.01
    105
    +0.14
    0.01
    Negative Logits
    ingle
    -1.54
    acetate
    -1.53
    "`
    -1.52
    vereign
    -1.48
    astern
    -1.44
    ogens
    -1.44
     deference
    -1.43
    "]
    -1.41
    >`
    -1.37
     "/
    -1.36
    POSITIVE LOGITS
    stown
    1.84
    ²
    1.80
    ¢
    1.67
    ¾
    1.66
    guide
    1.52
    ¿
    1.50
    elled
    1.48
    hesis
    1.48
     league
    1.43
    ½
    1.42
    Activations Density 0.019%

    No Known Activations