© 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. 1-RES-SM
    11. 25726
    Prev
    Next
    INDEX
    Explanations

    legal terms and references related to court cases and appeals

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    357
    +0.13
    0.7%
    189
    +0.11
    0.6%
    92
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    75
    +0.13
    0.01
    357
    +0.11
    0.01
    92
    +0.11
    0.02
    Negative Logits
    how
    -1.74
    lect
    -1.58
    what
    -1.57
    other
    -1.49
    ferentially
    -1.46
    cent
    -1.45
    epithelial
    -1.44
    irc
    -1.44
    iginally
    -1.41
    xygen
    -1.40
    POSITIVE LOGITS
    naire
    1.90
    AGES
    1.90
    ULAR
    1.74
    ARA
    1.72
    imus
    1.68
    £
    1.66
    inib
    1.57
    AGE
    1.56
    rä
    1.56
     CLAIM
    1.53
    Activations Density 0.083%

    No Known Activations