© 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. 0-MLP-SM
    11. 29096
    Prev
    Next
    INDEX
    Explanations

    references to the "boost" library in 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
    256
    +0.12
    0.6%
    430
    +0.11
    0.6%
    111
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    430
    +0.12
    0.01
    349
    +0.11
    0.01
    256
    +0.11
    0.01
    Negative Logits
    ¦
    -2.41
    ľ
    -2.38
    Ĥ¬
    -2.36
    ¿
    -2.30
    ľĵ
    -2.27
    Īĺ
    -2.26
    ĥ½
    -2.20
    ¿½
    -2.15
    ´
    -2.14
    ¾
    -2.07
    POSITIVE LOGITS
    "}](#
    1.73
    lectual
    1.66
     arsenal
    1.56
    limiting
    1.55
     años
    1.54
     reactors
    1.54
     modality
    1.53
     arm
    1.52
     programmes
    1.50
    arts
    1.43
    Activations Density 0.010%

    No Known Activations