© 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. Residuals
    5. 4-RES-SM
    6. 12037
    Prev
    Next
    INDEX
    Explanations

    terms related to bone health and related conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__res-sm_processed/4-res-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    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
    420
    +0.12
    0.7%
    93
    +0.12
    0.6%
    164
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    93
    +0.12
    0.01
    164
    +0.12
    0.01
    452
    +0.10
    0.01
    Negative Logits
    gmail
    -1.69
    essages
    -1.69
     concurring
    -1.66
    s
    -1.58
    edes
    -1.48
    ::::
    -1.48
    ottu
    -1.47
    ouds
    -1.45
     Honorable
    -1.44
     dissenting
    -1.44
    POSITIVE LOGITS
     marrow
    3.03
    head
    2.45
    heads
    2.32
     fractures
    2.25
     fracture
    2.13
     grafts
    2.07
     grafting
    2.05
     mineral
    1.92
     morph
    1.92
     tissue
    1.86
    Activations Density 0.032%

    No Known Activations