© 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. Residuals
    9. 4-RES-SM
    11. 14090
    Prev
    Next
    INDEX
    Explanations

    terms related to cancer treatment and related statistics

    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
    307
    +0.37
    2.2%
    306
    +0.28
    1.7%
    255
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    307
    +0.37
    0.24
    306
    +0.28
    0.13
    447
    +0.12
    0.15
    Negative Logits
     teachers
    -2.38
     students
    -2.37
     Teachers
    -2.21
     classrooms
    -2.17
    chool
    -2.12
     educators
    -2.12
     Elementary
    -2.08
     Teacher
    -2.05
     curriculum
    -1.99
     schools
    -1.97
    POSITIVE LOGITS
    ĻĤ
    3.07
    ĥ½
    2.82
    ↵
    2.81
    <|outofrange|>
    2.81
     ↵
    2.81
    2.81
     ↵
    2.81
    ↵
    2.81
    2.81
    <|outofrange|>
    2.81
    Activations Density 4.522%

    No Known Activations