© 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. 2-RES-SM
    11. 31238
    Prev
    Next
    INDEX
    Explanations

    occurrences of specific punctuation marks and their variations

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    66
    +0.13
    0.7%
    410
    +0.12
    0.7%
    505
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    66
    +0.13
    0.04
    50
    +0.12
    0.03
    201
    +0.11
    0.03
    Negative Logits
    onymous
    -1.75
    cription
    -1.74
    ESULT
    -1.69
    pute
    -1.68
    otypic
    -1.68
    ump
    -1.55
    phot
    -1.51
    oscope
    -1.50
    obox
    -1.49
    criptions
    -1.48
    POSITIVE LOGITS
    Ĭ
    2.77
    ¡
    2.71
    ŀ
    2.71
    IJ
    2.68
    ½
    2.61
    ¿
    2.60
    ®
    2.54
    Į
    2.50
    ¿½
    2.49
    §
    2.47
    Activations Density 0.175%

    No Known Activations