© 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. 0-MLP-SM
    11. 29148
    Prev
    Next
    INDEX
    Explanations

    questions starting with "What"

    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
    356
    +0.14
    0.7%
    457
    +0.13
    0.7%
    376
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    356
    +0.14
    0.07
    85
    +0.13
    0.06
    197
    +0.11
    0.06
    Negative Logits
    ´
    -1.65
    ATIONAL
    -1.60
    ======
    -1.56
    abbit
    -1.54
     SUMMARY
    -1.53
    OPE
    -1.52
    HTML
    -1.51
    ¬
    -1.50
     </
    -1.50
    rant
    -1.49
    POSITIVE LOGITS
    soever
    1.57
    ilda
    1.48
    vu
    1.45
    lli
    1.45
     sane
    1.42
    woke
    1.41
    osi
    1.41
     conditions
    1.40
    arda
    1.40
     ail
    1.39
    Activations Density 0.718%

    No Known Activations