© 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. 11027
    Prev
    Next
    INDEX
    Explanations

    prepositions and phrases indicating relationships between concepts

    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
    392
    +0.14
    0.8%
    30
    +0.14
    0.8%
    21
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    98
    +0.14
    0.01
    168
    +0.14
    0.01
    57
    +0.13
    0.01
    Negative Logits
     thereto
    -2.17
     hereto
    -1.86
    eno
    -1.73
    psin
    -1.71
     therefrom
    -1.68
    +/
    -1.64
     thereof
    -1.62
     accordingly
    -1.61
    +.
    -1.56
     thereon
    -1.52
    POSITIVE LOGITS
    ´
    2.89
    ļ
    2.67
    ↵
    2.64
    č↵
    2.64
    ↵
    2.64
    ↵↵
    2.64
                  ↵
    2.64
    2.64
    ↵  ↵
    2.64
    ↵
    2.64
    Activations Density 0.027%

    No Known Activations