© 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. 29389
    Prev
    Next
    INDEX
    Explanations

    references to computer code execution or processing commands

    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
    114
    +0.10
    0.6%
    184
    +0.10
    0.6%
    250
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.10
    0.01
    184
    +0.10
    0.01
    283
    +0.10
    0.01
    Negative Logits
    Īĺ
    -2.97
    ĨĴ
    -2.86
    ľĵ
    -2.76
    ĻĤ
    -2.43
    Ļª
    -2.40
    ĸ´
    -2.39
    Ł
    -2.33
    Ĥ¬
    -2.33
    ²
    -2.27
    º
    -2.26
    POSITIVE LOGITS
    recht
    2.25
    ware
    1.96
    etable
    1.87
    ruptcy
    1.85
    aret
    1.85
    ETS
    1.85
    etts
    1.82
    rooms
    1.78
    verts
    1.76
    laws
    1.74
    Activations Density 0.116%

    No Known Activations