© 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 EvalsExportsAPI 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. 26008
    Prev
    Next
    INDEX
    Explanations

    terms related to racing or motorsport

    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
    136
    +0.14
    0.8%
    122
    +0.13
    0.8%
    0
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    136
    +0.14
    -0.04
    47
    +0.13
    0.16
    153
    +0.12
    0.14
    Negative Logits
    ¿½
    -2.46
    Ĵ
    -2.07
    ŀ
    -2.04
    £
    -2.02
    ĵ
    -2.00
    Ļª
    -1.90
    Į
    -1.89
    ļ
    -1.85
    ķ
    -1.84
    ĸ
    -1.82
    POSITIVE LOGITS
    gue
    1.64
    rice
    1.52
     laterally
    1.45
     influ
    1.38
     08
    1.38
    offs
    1.36
    anges
    1.36
    ifice
    1.34
     thickness
    1.34
    ighs
    1.32
    Activations Density 4.236%

    No Known Activations