© 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. 28765
    Prev
    Next
    INDEX
    Explanations

    references to a specific person or character, particularly with the name "Dum."

    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
    369
    +0.16
    0.9%
    111
    +0.14
    0.8%
    477
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.16
    0.01
    59
    +0.14
    0.01
    94
    +0.13
    0.01
    Negative Logits
     myself
    -1.59
    izability
    -1.55
    izable
    -1.53
    rapped
    -1.47
    ization
    -1.46
     nature
    -1.44
    _."
    -1.43
     happening
    -1.43
     footsteps
    -1.41
     coli
    -1.39
    POSITIVE LOGITS
    uel
    1.89
    ál
    1.76
    uelle
    1.72
    ÅĨ
    1.62
    ankind
    1.61
    bugs
    1.59
     goodbye
    1.49
    lite
    1.49
     Price
    1.47
    arie
    1.43
    Activations Density 0.014%

    No Known Activations