© 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. 27558
    Prev
    Next
    INDEX
    Explanations

    terms related to resistance and tolerance in a medical or biological context

    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
    +0.16
    0.9%
    304
    +0.14
    0.8%
    199
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    304
    +0.16
    0.02
    42
    +0.14
    0.01
    199
    +0.13
    0.01
    Negative Logits
    lish
    -1.95
    ateurs
    -1.73
     grateful
    -1.67
    zbollah
    -1.65
    eks
    -1.64
    arat
    -1.63
    chen
    -1.61
     thankful
    -1.57
    antha
    -1.55
     vez
    -1.52
    POSITIVE LOGITS
     affecting
    1.84
     mechanisms
    1.80
    coat
    1.67
    fork
    1.66
    break
    1.65
     prevention
    1.65
     against
    1.64
     mechanism
    1.64
    Ł
    1.63
     variable
    1.61
    Activations Density 0.080%

    No Known Activations