© 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. 28915
    Prev
    Next
    INDEX
    Explanations

    occurrences of specific patterns or sequences in a data format

    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
    53
    +0.14
    0.8%
    321
    +0.12
    0.7%
    115
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    53
    +0.14
    0.02
    220
    +0.12
    0.01
    247
    +0.12
    0.01
    Negative Logits
    ño
    -1.53
    1371
    -1.49
    doctoral
    -1.47
     term
    -1.45
    litaxel
    -1.45
    ochrom
    -1.42
    owski
    -1.41
    openh
    -1.41
    auses
    -1.40
     jointly
    -1.39
    POSITIVE LOGITS
     loyalty
    1.79
     confidence
    1.55
     personality
    1.51
     allegiance
    1.50
     dex
    1.50
     robes
    1.47
     spice
    1.44
     willingness
    1.42
     kingdom
    1.41
    ()</
    1.41
    Activations Density 5.060%

    No Known Activations