© 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. 11150
    Prev
    Next
    INDEX
    Explanations

    references to pigs and related negative or humorous 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/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
    443
    +0.14
    0.8%
    307
    +0.13
    0.7%
    410
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    443
    +0.14
    0.06
    410
    +0.13
    0.06
    467
    +0.12
    0.04
    Negative Logits
    iginally
    -1.72
     order
    -1.56
     differentiable
    -1.52
    izable
    -1.46
     personnel
    -1.46
     caution
    -1.45
     include
    -1.35
     regards
    -1.33
    ases
    -1.33
    ives
    -1.32
    POSITIVE LOGITS
    ged
    3.52
    ging
    3.26
    gy
    3.20
    gle
    2.86
    gin
    2.73
    gers
    2.71
    gie
    2.68
    »¿
    2.59
    gins
    2.59
    gered
    2.58
    Activations Density 0.842%

    No Known Activations