© 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. 4-RES-SM
    11. 12901
    Prev
    Next
    INDEX
    Explanations

    adjectives and adverbs related to degree or comparison

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    78
    +0.22
    1.3%
    83
    +0.13
    0.8%
    387
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    375
    +0.22
    0.10
    2
    +0.13
    0.10
    387
    +0.13
    0.10
    Negative Logits
    ATIONS
    -1.95
    "}](#
    -1.93
    ician
    -1.82
    £
    -1.81
    ability
    -1.80
    ações
    -1.78
    icides
    -1.78
    lection
    -1.77
    iciency
    -1.76
    isions
    -1.73
    POSITIVE LOGITS
     easy
    2.36
     difficult
    2.10
     helpful
    2.02
     prone
    1.99
     expensive
    1.98
     feasible
    1.97
     likely
    1.97
     stable
    1.97
     worth
    1.96
     challenging
    1.95
    Activations Density 0.612%

    No Known Activations