© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. MLP Post
    9. 2-MLP-SM
    11. 22864
    Prev
    Next
    INDEX
    Explanations

    phrases related to medical treatments and interventions

    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/2-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.2.hook_mlp_out
    Hook Layer
    2
    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
    178
    +0.15
    0.9%
    333
    +0.11
    0.6%
    33
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    318
    +0.15
    0.01
    88
    +0.11
    0.01
    404
    +0.10
    0.01
    Negative Logits
     definitions
    -1.79
     hypotheses
    -1.63
     terminology
    -1.53
     authors
    -1.48
    ureus
    -1.47
     arguments
    -1.46
     assumptions
    -1.45
     acup
    -1.45
    opsies
    -1.43
     Plaintiffs
    -1.43
    POSITIVE LOGITS
    ĥ½
    2.16
    ģ
    1.92
    Ķ
    1.83
    ...](
    1.74
    ľĵ
    1.70
    ķ
    1.69
    Ŀ
    1.68
    ĸ
    1.65
    Ī
    1.64
    owned
    1.64
    Activations Density 0.144%

    No Known Activations