© 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. 10083
    Prev
    Next
    INDEX
    Explanations

    terms related to cancer and its various forms

    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
    156
    +0.18
    1.0%
    405
    +0.16
    0.9%
    48
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    148
    +0.18
    0.02
    385
    +0.16
    0.01
    48
    +0.12
    0.03
    Negative Logits
    s
    -1.87
    LY
    -1.51
     parentheses
    -1.47
    e
    -1.47
     tempo
    -1.46
    dream
    -1.45
    ingale
    -1.44
    lain
    -1.43
    bbe
    -1.42
    sworth
    -1.38
    POSITIVE LOGITS
    Ĥ
    4.66
    ĩ
    4.58
    Ļ
    4.51
    Ĩ
    4.45
    ħ
    4.42
    «
    4.38
    ¢
    4.31
    ĸ
    4.27
    ª
    4.24
    ²
    4.18
    Activations Density 0.156%

    No Known Activations