© 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. 25620
    Prev
    Next
    INDEX
    Explanations

    references to chemical compounds and their properties

    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
    250
    +0.18
    1.0%
    258
    +0.15
    0.9%
    412
    +0.15
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    250
    +0.18
    0.11
    412
    +0.15
    0.09
    177
    +0.15
    0.06
    Negative Logits
    ľĵ
    -1.95
    Ļª
    -1.95
    ÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤ
    -1.72
    ±
    -1.72
    ´
    -1.69
    Īĺ
    -1.67
    iginally
    -1.66
    ÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤ
    -1.64
    ĸ´
    -1.62
    -1.62
    POSITIVE LOGITS
    imum
    1.93
    andro
    1.63
    »,
    1.55
    ».
    1.51
    .“
    1.44
    arro
    1.44
    uden
    1.41
    imus
    1.38
    orum
    1.38
    iom
    1.37
    Activations Density 0.387%

    No Known Activations