© 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. 11329
    Prev
    Next
    INDEX
    Explanations

    phrases related to the evaluation and impact of organizations involved in development and social policies

    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
    307
    +0.33
    2.2%
    348
    +0.21
    1.4%
    306
    +0.21
    1.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    307
    +0.33
    0.19
    306
    +0.21
    0.10
    447
    +0.21
    0.13
    Negative Logits
    »¿
    -2.56
    ī
    -2.32
    Ģ
    -2.04
    ĻĤ
    -1.95
    Ĺ
    -1.86
    ®
    -1.85
    »
    -1.82
    ¸
    -1.78
    ¶
    -1.73
    °
    -1.72
    POSITIVE LOGITS
     different
    1.86
     influencing
    1.68
     elucid
    1.68
     debates
    1.65
     evaluations
    1.64
     broader
    1.62
     various
    1.60
     empirical
    1.60
     discussions
    1.59
     assessments
    1.58
    Activations Density 2.419%

    No Known Activations