© 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. 12922
    Prev
    Next
    INDEX
    Explanations

    legal terminology and references within judicial contexts

    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
    293
    +0.12
    0.7%
    410
    +0.11
    0.6%
    21
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    410
    +0.12
    0.08
    21
    +0.11
    0.04
    168
    +0.11
    0.04
    Negative Logits
     {}
    -1.85
     trillion
    -1.61
    **~
    -1.60
    soever
    -1.59
    ocracy
    -1.56
     recognise
    -1.54
    SUCCESS
    -1.53
    ”.
    -1.51
     realise
    -1.51
    ten
    -1.50
    POSITIVE LOGITS
    <|outofrange|>
    3.03
    ↵
    3.03
    ↵↵
    3.03
     ↵
    3.03
    ↵
    3.03
    č↵
    3.03
    3.03
    ↵
    3.03
    ↵    ↵
    3.03
    ↵
    3.03
    Activations Density 0.431%

    No Known Activations