© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 2-RES-SM
    11. 27476
    Prev
    Next
    INDEX
    Explanations

    legal terminology and proceedings related to 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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    292
    +0.14
    0.8%
    478
    +0.11
    0.6%
    491
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    168
    +0.14
    0.02
    87
    +0.11
    0.02
    174
    +0.11
    0.02
    Negative Logits
    )</
    -1.89
    )].
    -1.76
    oning
    -1.72
    )](
    -1.68
    )">
    -1.61
    ym
    -1.55
    )",
    -1.55
    ()).
    -1.52
    )."
    -1.50
    )',
    -1.47
    POSITIVE LOGITS
    ¦
    3.77
    ·
    3.54
    ¸
    3.50
    ¤
    3.40
    ĵ
    3.38
    Īĺ
    3.34
    ĥ½
    3.30
    ķ
    3.26
    Ĥ
    3.20
    ¹
    3.19
    Activations Density 0.054%

    No Known Activations