© 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. 4-RES-SM
    11. 14630
    Prev
    Next
    INDEX
    Explanations

    references to LGBTQ+ issues and discussions surrounding same-sex marriage

    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
    168
    +0.13
    0.7%
    186
    +0.12
    0.7%
    417
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    186
    +0.13
    0.12
    418
    +0.12
    0.04
    168
    +0.11
    0.10
    Negative Logits
    İ
    -3.76
    »¿
    -3.51
    Īĺ
    -3.46
    ¤
    -3.42
    ľĵ
    -3.28
    Ĥ
    -3.18
    ↵↵
    -3.18
    ↵↵
    -3.18
    -3.18
    -3.18
    POSITIVE LOGITS
     LGBT
    4.36
     gay
    4.09
     homosexual
    3.90
     heterosexual
    3.82
     homosexuality
    3.80
     transgender
    3.80
     sexuality
    3.67
     lesbian
    3.66
     gender
    3.54
     sexual
    3.40
    Activations Density 2.697%

    No Known Activations