© 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. 27128
    Prev
    Next
    INDEX
    Explanations

    specialized methods or strategies in various contexts

    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
    +0.27
    1.6%
    376
    +0.16
    1.0%
    77
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    77
    +0.27
    0.02
    262
    +0.16
    0.02
    461
    +0.13
    0.01
    Negative Logits
    ĥ½
    -3.10
    §
    -2.80
    »¿
    -2.75
    Ļª
    -2.65
    ¼
    -2.47
    į
    -2.39
    »
    -2.37
    ³
    -2.33
    ĥ
    -2.33
    ·¸
    -2.27
    POSITIVE LOGITS
    urgical
    1.79
    heet
    1.65
    urg
    1.51
    ica
    1.50
    ics
    1.50
    erv
    1.49
    este
    1.49
    hell
    1.46
    etting
    1.46
    cue
    1.45
    Activations Density 0.567%

    No Known Activations