© 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. 29214
    Prev
    Next
    INDEX
    Explanations

    specific identifiers and markers related to cellular biology and cancer research

    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
    270
    +0.14
    0.8%
    192
    +0.11
    0.6%
    183
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    270
    +0.14
    0.02
    262
    +0.11
    0.02
    134
    +0.10
    0.02
    Negative Logits
    ±
    -2.77
    »
    -2.60
    ¿½
    -2.51
    ¾
    -2.48
    ¼
    -2.40
    Ŀ
    -2.38
    ·¸
    -2.37
    ĵ
    -2.28
    ī
    -2.27
    ŀ
    -2.27
    POSITIVE LOGITS
     nominations
    1.77
    rition
    1.72
    ocortic
    1.68
     ranks
    1.60
    illard
    1.59
    rente
    1.56
    less
    1.56
    enez
    1.53
    imab
    1.53
    edia
    1.48
    Activations Density 0.201%

    No Known Activations