© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. MLP Post
    9. 2-MLP-SM
    11. 25310
    Prev
    Next
    INDEX
    Explanations

    the concept of re-evaluation or revitalization 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/2-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.2.hook_mlp_out
    Hook Layer
    2
    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
    +0.30
    1.7%
    475
    +0.13
    0.8%
    23
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    475
    +0.30
    0.03
    181
    +0.13
    0.04
    253
    +0.12
    0.02
    Negative Logits
    ĸ
    -1.75
    thood
    -1.54
    bugs
    -1.36
    ){#
    -1.35
    cdn
    -1.33
    erne
    -1.33
    Wednesday
    -1.33
    izumab
    -1.32
    rbrack
    -1.30
    hton
    -1.30
    POSITIVE LOGITS
     distinguished
    1.80
     observed
    1.50
     instituted
    1.48
     _
    1.45
     initiated
    1.44
     joined
    1.38
    ieves
    1.38
     attenuated
    1.36
    ax
    1.36
    rias
    1.34
    Activations Density 0.445%

    No Known Activations