© 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. 29560
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Associated," indicating a focus on associated entities or organizations

    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
    156
    +0.14
    0.8%
    376
    +0.14
    0.8%
    148
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    280
    +0.14
    0.01
    227
    +0.14
    0.01
    160
    +0.13
    0.01
    Negative Logits
    ij
    -2.53
    Ĥ
    -2.45
    ĭ
    -2.31
    ¯
    -2.27
    Ĵ
    -2.26
    ´
    -2.23
    ¸
    -2.21
    ĥ½
    -2.19
    ı
    -2.18
    ĸ´
    -2.17
    POSITIVE LOGITS
    ultan
    1.55
    fonts
    1.45
    lace
    1.43
    arroll
    1.39
    ités
    1.37
    fields
    1.35
    ienne
    1.35
    heads
    1.34
    pose
    1.34
    haven
    1.34
    Activations Density 0.010%

    No Known Activations