© 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. 13130
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal proceedings and court cases

    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
    21
    +0.24
    1.4%
    78
    +0.17
    1.0%
    27
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    65
    +0.24
    0.03
    270
    +0.17
    0.02
    34
    +0.10
    0.02
    Negative Logits
     machinery
    -1.46
     translocation
    -1.40
     encode
    -1.38
     others
    -1.38
    plastic
    -1.34
     flock
    -1.34
     disruption
    -1.34
     pack
    -1.31
     scaff
    -1.28
     repaired
    -1.27
    POSITIVE LOGITS
    ®
    2.13
    Ģ
    2.12
    Ĩ
    1.95
    ¥
    1.94
    Ī
    1.93
    «
    1.90
    ī
    1.80
    ¤
    1.80
    Ĥ¬
    1.79
    Ŀ
    1.79
    Activations Density 0.045%

    No Known Activations