© 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. 1-RES-SM
    11. 24627
    Prev
    Next
    INDEX
    Explanations

    references to volunteering activities and volunteers

    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
    156
    +0.21
    1.2%
    225
    +0.11
    0.7%
    0
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    251
    +0.21
    0.02
    156
    +0.11
    0.03
    321
    +0.11
    0.02
    Negative Logits
    ĥ½
    -2.40
    ¶
    -2.15
    ·
    -2.12
    ©
    -2.10
    ĺ
    -2.00
    uke
    -1.82
    ĵ
    -1.79
    ¯
    -1.79
    ¬
    -1.76
    ı
    -1.76
    POSITIVE LOGITS
    istration
    1.65
    ester
    1.63
    ery
    1.57
    onder
    1.54
    ering
    1.54
    erals
    1.53
    maid
    1.52
    ettle
    1.50
    oter
    1.49
    eral
    1.48
    Activations Density 0.281%

    No Known Activations