© 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. 24441
    Prev
    Next
    INDEX
    Explanations

    negations and phrases indicating what cannot be done or achieved

    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
    266
    +0.13
    0.7%
    176
    +0.11
    0.6%
    250
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    266
    +0.13
    0.03
    250
    +0.11
    0.04
    328
    +0.10
    0.04
    Negative Logits
    ¬
    -1.70
    ERY
    -1.69
    FORMATION
    -1.67
    ancies
    -1.67
     nv
    -1.50
    ķ
    -1.46
    nv
    -1.42
    ements
    -1.41
    ¥
    -1.39
    naments
    -1.39
    POSITIVE LOGITS
    forge
    1.61
     meaning
    1.59
    heets
    1.54
    heet
    1.48
    ibel
    1.47
    onate
    1.47
    lav
    1.41
    ono
    1.41
     lungs
    1.40
    ales
    1.39
    Activations Density 0.204%

    No Known Activations