© 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. 12667
    Prev
    Next
    INDEX
    Explanations

    terms related to legal cases and court proceedings

    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
    186
    +0.13
    0.8%
    220
    +0.13
    0.7%
    369
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    168
    +0.13
    0.03
    393
    +0.13
    0.02
    319
    +0.11
    0.02
    Negative Logits
    canvas
    -1.58
    ids
    -1.55
    /#
    -1.52
    atra
    -1.49
    vast
    -1.49
    ect
    -1.48
    egan
    -1.46
    otte
    -1.45
     needs
    -1.39
    orget
    -1.38
    POSITIVE LOGITS
    ·
    4.06
    ¹
    4.05
    ĵ
    3.94
    º
    3.93
    ¤
    3.84
    ĥ½
    3.79
    ĸ´
    3.78
    ²
    3.73
    Ĥ¬
    3.71
    ·¸
    3.71
    Activations Density 0.096%

    No Known Activations