© 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. 28575
    Prev
    Next
    INDEX
    Explanations

    content related to adult entertainment, specifically focusing on pornographic material and associated themes

    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
    498
    +0.13
    0.7%
    301
    +0.12
    0.7%
    440
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    56
    +0.13
    -0.03
    269
    +0.12
    0.06
    282
    +0.12
    0.04
    Negative Logits
     Lemma
    -1.59
    frastructure
    -1.58
     roads
    -1.52
     livestock
    -1.52
     maps
    -1.51
     kinases
    -1.47
    igate
    -1.45
     Plains
    -1.43
     Representatives
    -1.42
    ploy
    -1.42
    POSITIVE LOGITS
    male
    2.26
     orgasm
    2.20
     porn
    2.14
     sex
    1.99
    Sex
    1.97
     Sex
    1.94
     erotic
    1.93
     menstrual
    1.86
     anal
    1.84
     pregnancy
    1.83
    Activations Density 1.907%

    No Known Activations