© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 27049
    Prev
    Next
    INDEX
    Explanations

    instances of the word "outcome."

    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
    156
    +0.17
    1.0%
    178
    +0.14
    0.8%
    219
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    178
    +0.17
    0.02
    213
    +0.14
    0.01
    219
    +0.13
    0.01
    Negative Logits
    ]>
    -1.84
     Respondents
    -1.69
    ]=
    -1.65
    ARRANT
    -1.61
    harma
    -1.58
    hire
    -1.57
     preponderance
    -1.49
     exclusively
    -1.48
    faith
    -1.44
    ]{}\_[
    -1.44
    POSITIVE LOGITS
     retrieval
    1.73
     footing
    1.58
    isp
    1.54
     bird
    1.53
     palate
    1.52
    hole
    1.51
    ipers
    1.49
    imet
    1.48
     stre
    1.48
    tables
    1.43
    Activations Density 0.154%

    No Known Activations