© 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. 29407
    Prev
    Next
    INDEX
    Explanations

    instances of the word "rent."

    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
    382
    +0.12
    0.7%
    503
    +0.11
    0.7%
    117
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    382
    +0.12
    0.01
    264
    +0.11
    0.01
    503
    +0.10
    0.01
    Negative Logits
     {}
    -1.68
     treated
    -1.58
     normal
    -1.52
    usterity
    -1.47
     mouse
    -1.47
     '')
    -1.46
     expect
    -1.45
     ...)
    -1.45
     mean
    -1.45
     breathe
    -1.44
    POSITIVE LOGITS
    uximab
    2.24
    ophone
    2.15
    anguage
    2.05
          ↵
    1.98
    ↵↵↵
    1.98
    ↵
    1.98
    ↵
    1.98
    1.98
    1.98
                  ↵
    1.98
    Activations Density 0.008%

    No Known Activations