© 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. 28484
    Prev
    Next
    INDEX
    Explanations

    references to academic programs or fields of study

    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
    +0.12
    0.7%
    448
    +0.11
    0.6%
    124
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    448
    +0.12
    0.03
    124
    +0.11
    0.03
    343
    +0.10
    0.03
    Negative Logits
     present
    -1.54
     microscope
    -1.46
     TRUE
    -1.45
    ABLE
    -1.39
     boolean
    -1.36
     propensity
    -1.35
     situ
    -1.33
     enabled
    -1.33
    ENA
    -1.31
    icate
    -1.31
    POSITIVE LOGITS
    Į
    2.01
    Īĺ
    2.00
    holes
    1.72
    ¨
    1.68
    stro
    1.68
    °
    1.63
     hur
    1.62
     orders
    1.62
    ities
    1.59
    »¿
    1.59
    Activations Density 1.189%

    No Known Activations