© 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. 26452
    Prev
    Next
    INDEX
    Explanations

    instances of the word "large" or 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
    81
    +0.14
    0.8%
    457
    +0.14
    0.8%
    410
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    272
    +0.14
    0.01
    428
    +0.14
    0.01
    111
    +0.13
    0.01
    Negative Logits
    ters
    -1.79
    hol
    -1.72
    oval
    -1.58
    aded
    -1.56
    zip
    -1.56
    ?'
    -1.52
    ursed
    -1.50
    tern
    -1.49
    omerase
    -1.48
     therefrom
    -1.48
    POSITIVE LOGITS
    ŀ
    2.83
    ħ
    2.77
    ģ
    2.76
    ĻĤ
    2.75
    £
    2.74
    ¡
    2.72
    ·
    2.54
    Ľ
    2.50
    Ĵ
    2.49
    ²
    2.48
    Activations Density 0.284%

    No Known Activations