© 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. 14651
    Prev
    Next
    INDEX
    Explanations

    references to different versions of UTF encoding

    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
    21
    +0.26
    1.5%
    255
    +0.14
    0.8%
    78
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    133
    +0.26
    0.01
    349
    +0.14
    0.01
    255
    +0.12
    0.00
    Negative Logits
    continue
    -1.56
     schedules
    -1.54
     inclusion
    -1.47
     steady
    -1.43
     stop
    -1.39
     stay
    -1.39
    culate
    -1.37
    icult
    -1.37
     commute
    -1.33
    ions
    -1.31
    POSITIVE LOGITS
    åŃĹ
    1.87
    "?>
    1.85
    à±
    1.66
    unicode
    1.63
    ">"
    1.55
    jä
    1.55
    á½IJ
    1.54
    CDATA
    1.52
    áĥĶ
    1.51
     namespace
    1.48
    Activations Density 0.048%

    No Known Activations