© 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. 25443
    Prev
    Next
    INDEX
    Explanations

    the presence of type definitions in programming code

    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
    244
    +0.14
    0.8%
    339
    +0.12
    0.7%
    457
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    244
    +0.14
    0.02
    339
    +0.12
    0.02
    419
    +0.12
    0.02
    Negative Logits
     WHERE
    -1.60
    ibo
    -1.54
     sense
    -1.52
     traced
    -1.49
     persist
    -1.46
     considered
    -1.43
    \)
    -1.42
    olate
    -1.42
     propagated
    -1.41
    )](#
    -1.40
    POSITIVE LOGITS
    ¡
    2.87
    £
    2.79
    §
    2.76
    ķ
    2.64
    º
    2.57
    ļ
    2.57
    ©
    2.54
    ®
    2.52
    Ĵ
    2.52
    Ĺ
    2.49
    Activations Density 0.007%

    No Known Activations