© 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. 28731
    Prev
    Next
    INDEX
    Explanations

    patterns of formatting in textual data, such as decoration or emphasis markers

    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
    176
    +0.15
    0.9%
    261
    +0.13
    0.7%
    250
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    261
    +0.15
    0.01
    176
    +0.13
    0.01
    230
    +0.12
    0.01
    Negative Logits
    omer
    -1.68
     bond
    -1.67
    ubot
    -1.64
    pite
    -1.61
    irc
    -1.60
    rypt
    -1.58
     undergo
    -1.57
     comply
    -1.55
    ird
    -1.49
    ically
    -1.49
    POSITIVE LOGITS
    ~~~
    1.77
     fiction
    1.63
    rooms
    1.63
     Someone
    1.50
     hints
    1.47
     bathrooms
    1.39
    stylesheet
    1.37
     generality
    1.36
    dates
    1.36
    room
    1.34
    Activations Density 0.010%

    No Known Activations