© 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. 26684
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing severity or critical conditions

    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
    250
    +0.12
    0.6%
    116
    +0.11
    0.6%
    282
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    494
    +0.12
    0.45
    209
    +0.11
    0.29
    402
    +0.11
    0.26
    Negative Logits
    hire
    -1.83
     behind
    -1.79
     sales
    -1.61
    anguage
    -1.49
    ocyanate
    -1.49
     responsible
    -1.47
    ila
    -1.46
    urd
    -1.46
    atile
    -1.44
    raiser
    -1.41
    POSITIVE LOGITS
    ĨĴ
    1.54
    ¹
    1.50
    »
    1.48
     curly
    1.46
    stdout
    1.44
    Ģ
    1.40
    printStackTrace
    1.37
     mucosal
    1.33
    asan
    1.32
     oral
    1.31
    Activations Density 1.575%

    No Known Activations