© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 12045
    Prev
    Next
    INDEX
    Explanations

    expressions of degree or intensity, particularly in relation to judgments and evaluations

    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
    156
    +0.16
    0.9%
    223
    +0.12
    0.6%
    312
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    18
    +0.16
    0.11
    223
    +0.12
    0.05
    291
    +0.11
    0.05
    Negative Logits
    ા
    -2.12
    ி
    -2.02
    à«ĩ
    -1.95
    ίαÏĤ
    -1.90
    à¯ģ
    -1.89
    à¯
    -1.88
    ophagus
    -1.84
    à¯į
    -1.82
    à³
    -1.77
    ি
    -1.76
    POSITIVE LOGITS
     precision
    2.38
     scrutiny
    2.38
     assistance
    2.35
     guidance
    2.33
     supervision
    2.33
     clarity
    2.30
     consideration
    2.30
     certainty
    2.29
     accuracy
    2.28
     comfort
    2.27
    Activations Density 1.188%

    No Known Activations