© 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. 27608
    Prev
    Next
    INDEX
    Explanations

    scientific terms related to medical studies and treatments

    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
    23
    +0.13
    0.7%
    315
    +0.12
    0.7%
    326
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    138
    +0.13
    0.03
    418
    +0.12
    -0.01
    321
    +0.12
    0.02
    Negative Logits
    nament
    -1.84
    lite
    -1.55
    gio
    -1.53
     hire
    -1.49
     **
    -1.44
     ****
    -1.44
    iper
    -1.42
    uncher
    -1.40
     fuck
    -1.39
    "—
    -1.38
    POSITIVE LOGITS
    Ĺ
    2.67
    ł
    2.64
    ¨
    2.60
    ³
    2.47
    Ń
    2.46
    ĵ
    2.46
    ·
    2.41
    Ĩ
    2.41
    ħ
    2.37
    ĩ
    2.37
    Activations Density 0.216%

    No Known Activations