© 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. 29954
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "impro" indicating improvisation or improvisation-related content

    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
    111
    +0.14
    0.8%
    410
    +0.11
    0.6%
    67
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    240
    +0.14
    0.01
    111
    +0.11
    0.01
    67
    +0.11
    0.01
    Negative Logits
     Foundation
    -1.44
    imension
    -1.39
    AMP
    -1.38
    lander
    -1.33
    size
    -1.29
     descent
    -1.29
    athe
    -1.28
    ucht
    -1.27
     Superior
    -1.27
     felony
    -1.27
    POSITIVE LOGITS
    ĸ
    2.47
    ı
    2.41
    ¬
    2.35
    ±
    2.33
    Ĵ
    2.31
    2.21
    2.21
    ↵
    2.21
    ↵↵↵
    2.21
    ↵
    2.21
    Activations Density 0.339%

    No Known Activations