© 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. 25987
    Prev
    Next
    INDEX
    Explanations

    references to a specific individual named Joe

    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
    +0.19
    1.1%
    369
    +0.16
    1.0%
    357
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    357
    +0.19
    0.03
    308
    +0.16
    0.02
    86
    +0.14
    0.02
    Negative Logits
    rapy
    -1.97
     former
    -1.74
    rap
    -1.73
    rapeutics
    -1.62
     transgender
    -1.54
     child
    -1.53
    board
    -1.52
     '</
    -1.47
     second
    -1.46
     female
    -1.46
    POSITIVE LOGITS
    hole
    2.02
    issance
    1.91
    lei
    1.82
    holes
    1.81
    quito
    1.76
    ÃŃc
    1.68
    opan
    1.64
    's
    1.62
    ulence
    1.62
    cloth
    1.62
    Activations Density 0.013%

    No Known Activations