© 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. 2-RES-SM
    11. 10166
    Prev
    Next
    INDEX
    Explanations

    references to healthcare and medical institutions

    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
    308
    +0.12
    0.7%
    400
    +0.12
    0.7%
    143
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    55
    +0.12
    0.10
    57
    +0.12
    0.09
    167
    +0.12
    0.04
    Negative Logits
     plotted
    -1.44
    rolled
    -1.41
     heck
    -1.40
    quart
    -1.40
     voy
    -1.35
    keit
    -1.30
     helm
    -1.28
     grapes
    -1.28
     plot
    -1.27
     Florence
    -1.21
    POSITIVE LOGITS
    RON
    1.59
    )):
    1.58
    juvant
    1.52
    )),
    1.43
    ))$
    1.40
    ))$.
    1.39
    ).)
    1.38
    atures
    1.38
    ))$,
    1.38
    friend
    1.36
    Activations Density 4.155%

    No Known Activations