© 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. 13985
    Prev
    Next
    INDEX
    Explanations

    references to professional experience and expertise

    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
    365
    +0.14
    0.8%
    246
    +0.13
    0.7%
    241
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    241
    +0.14
    0.03
    246
    +0.13
    0.03
    365
    +0.12
    0.03
    Negative Logits
    Ģ
    -3.44
    ĻĤ
    -3.39
    į
    -3.28
    ¯
    -3.28
    ¤
    -3.28
    Ń
    -3.20
    ´
    -3.11
    ¿
    -3.10
    IJ
    -3.08
    ½
    -3.02
    POSITIVE LOGITS
    ional
    1.85
    ful
    1.83
    ground
    1.67
    ral
    1.66
    ingale
    1.65
    grounds
    1.64
     card
    1.55
    ricular
    1.51
    antry
    1.48
    fulness
    1.48
    Activations Density 0.175%

    No Known Activations