© 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. 31344
    Prev
    Next
    INDEX
    Explanations

    words related to biological processes and molecular interactions

    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
    156
    +0.30
    1.8%
    47
    +0.20
    1.2%
    23
    +0.17
    1.0%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    310
    +0.30
    0.05
    23
    +0.20
    0.06
    47
    +0.17
    0.06
    Negative Logits
     pdf
    -1.54
     broch
    -1.43
    rika
    -1.43
    VERS
    -1.42
     calculator
    -1.42
    ograph
    -1.40
    giene
    -1.39
    ynote
    -1.38
    ème
    -1.37
     checklist
    -1.37
    POSITIVE LOGITS
    ¶
    4.49
    IJ
    4.42
    º
    4.38
    ¿
    4.31
    ĸ
    4.26
    Ĩ
    4.26
    ĻĤ
    4.11
    »¿
    4.11
    Ĥ¬
    4.09
    Ĵ
    4.00
    Activations Density 0.453%

    No Known Activations