© 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. 13547
    Prev
    Next
    INDEX
    Explanations

    terms related to legal definitions and statutes

    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
    58
    +0.16
    0.9%
    155
    +0.15
    0.8%
    168
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    225
    +0.16
    0.10
    247
    +0.15
    0.06
    155
    +0.14
    0.04
    Negative Logits
    ľĵ
    -2.31
    ļ
    -2.16
    ĻĤ
    -2.14
    Īĺ
    -2.03
    µ
    -1.96
    ĥ
    -1.94
    ¬
    -1.92
    į
    -1.89
    Ĺ
    -1.89
    »
    -1.88
    POSITIVE LOGITS
     abbrev
    3.32
     surname
    3.28
     terminology
    3.15
     meanings
    3.06
     phrase
    3.04
     noun
    3.02
     referring
    3.01
     nickname
    2.99
     suffix
    2.96
     coined
    2.90
    Activations Density 1.888%

    No Known Activations