© 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. 31865
    Prev
    Next
    INDEX
    Explanations

    occurrences of JSON object syntax

    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
    274
    +0.12
    0.7%
    396
    +0.12
    0.7%
    292
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    188
    +0.12
    0.01
    51
    +0.12
    0.02
    213
    +0.11
    0.02
    Negative Logits
    ical
    -1.63
    ubot
    -1.51
    augh
    -1.45
     served
    -1.41
    ittle
    -1.41
    matched
    -1.40
    otten
    -1.40
    orr
    -1.39
     deserve
    -1.38
    adier
    -1.37
    POSITIVE LOGITS
    ¥
    1.81
     XL
    1.50
    ostics
    1.45
    geometry
    1.44
    axes
    1.43
     nombre
    1.43
    YY
    1.42
    IJ
    1.40
    serial
    1.40
     geom
    1.40
    Activations Density 0.097%

    No Known Activations