© 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. 24403
    Prev
    Next
    INDEX
    Explanations

    adverbs indicating frequency

    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
    103
    +0.15
    0.9%
    217
    +0.12
    0.7%
    98
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    103
    +0.15
    0.08
    213
    +0.12
    0.07
    225
    +0.12
    0.06
    Negative Logits
    CDATA
    -2.15
    à±ģ
    -1.79
     mild
    -1.64
    orems
    -1.55
    fected
    -1.50
    âĢ¦]
    -1.48
    à°¿
    -1.48
    translation
    -1.48
    translated
    -1.46
    à±
    -1.44
    POSITIVE LOGITS
    ivity
    1.68
     ranks
    1.62
    ://
    1.61
    ¿½
    1.60
    ®
    1.58
    blogger
    1.56
    lei
    1.52
    ery
    1.52
    ello
    1.51
    ĸ
    1.51
    Activations Density 0.627%

    No Known Activations