© 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. 2-MLP-SM
    11. 25023
    Prev
    Next
    INDEX
    Explanations

    terms related to prostate cancer and urinary incontinence

    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
    450
    +0.13
    0.7%
    156
    +0.12
    0.6%
    49
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    450
    +0.13
    0.04
    23
    +0.12
    0.02
    393
    +0.11
    0.01
    Negative Logits
    plants
    -1.66
    books
    -1.59
    .).
    -1.58
    »¿
    -1.57
     ages
    -1.53
    /)
    -1.51
     nuclei
    -1.51
     theaters
    -1.47
    )–
    -1.47
    oside
    -1.43
    POSITIVE LOGITS
    ORM
    1.57
    udd
    1.44
    illance
    1.44
    idegger
    1.42
     Abdullah
    1.40
     Er
    1.39
     Dew
    1.38
     Dirac
    1.36
    inition
    1.35
     ED
    1.35
    Activations Density 0.519%

    No Known Activations