© 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. 30628
    Prev
    Next
    INDEX
    Explanations

    references to the name "Albert" and its variations

    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
    43
    +0.11
    0.6%
    115
    +0.11
    0.6%
    499
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    43
    +0.11
    0.01
    499
    +0.11
    0.01
    411
    +0.11
    0.01
    Negative Logits
    ı
    -2.57
    Ĭ
    -2.45
    »¿
    -2.35
    Ĥ¬
    -2.28
    ĥ½
    -2.26
    ·¸
    -2.25
    Ĩ
    -2.24
    ĸ´
    -2.24
    ´
    -2.19
    į
    -2.11
    POSITIVE LOGITS
    ios
    1.85
    edly
    1.71
    iously
    1.63
    iop
    1.60
    stadt
    1.59
     Einstein
    1.54
    park
    1.53
    itud
    1.49
    enstein
    1.49
    shire
    1.47
    Activations Density 0.013%

    No Known Activations