© 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
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 0-MLP-SM
    6. 28209
    Prev
    Next
    INDEX
    Explanations

    visual elements related to icons

    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
    376
    +0.10
    0.6%
    177
    +0.09
    0.5%
    286
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    506
    +0.10
    0.01
    332
    +0.09
    0.01
    177
    +0.09
    0.01
    Negative Logits
    '?"
    -1.61
     ')
    -1.57
     assume
    -1.56
    "?"
    -1.56
    '))
    -1.54
    '));
    -1.51
     your
    -1.49
    unnumbered
    -1.49
    angling
    -1.48
    omething
    -1.48
    POSITIVE LOGITS
    lite
    2.22
    nement
    2.07
    ist
    2.06
    face
    2.04
    istas
    1.99
    finder
    1.95
    ista
    1.79
    nel
    1.78
    nell
    1.70
    chair
    1.68
    Activations Density 0.055%

    No Known Activations