© 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. 26642
    Prev
    Next
    INDEX
    Explanations

    phrases related to comparisons and contrasts

    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
    335
    +0.17
    0.9%
    221
    +0.13
    0.7%
    130
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    335
    +0.17
    0.02
    221
    +0.13
    0.02
    54
    +0.11
    0.02
    Negative Logits
    ³
    -2.30
    ĻĤ
    -2.23
    Ħ
    -2.18
    ¿
    -2.09
    ±
    -2.07
    Ļ
    -2.00
    »¿
    -1.96
    Ĥ¬
    -1.90
    ¼
    -1.90
    į
    -1.88
    POSITIVE LOGITS
    ible
    1.98
    IBLE
    1.69
    inho
    1.65
    able
    1.64
    thouse
    1.60
    vin
    1.59
    acting
    1.57
    ifs
    1.56
    ately
    1.52
    omination
    1.49
    Activations Density 0.017%

    No Known Activations