© 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. Residuals
    9. 1-RES-SM
    11. 26054
    Prev
    Next
    INDEX
    Explanations

    technical jargon and keywords related to computing and programming

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    17
    +0.31
    1.8%
    111
    +0.16
    1.0%
    369
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    380
    +0.31
    0.07
    17
    +0.16
    0.03
    369
    +0.14
    0.05
    Negative Logits
     Dad
    -1.68
     _"
    -1.52
     '
    -1.52
     ">
    -1.50
    wered
    -1.41
    >
    -1.40
    visibility
    -1.35
     sudden
    -1.31
    otransferase
    -1.30
    ãģĿãģĨ
    -1.29
    POSITIVE LOGITS
    Ĵ
    2.56
    ®
    2.43
    ĻĤ
    2.41
    Ģ
    2.33
    į
    2.28
    ĥ½
    2.26
    ↵
    2.17
    ↵
    2.17
    ↵
    2.17
    2.17
    Activations Density 0.942%

    No Known Activations