© 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. 29370
    Prev
    Next
    INDEX
    Explanations

    references to "pleasure" and related concepts

    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
    164
    +0.16
    0.9%
    139
    +0.13
    0.7%
    369
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    164
    +0.16
    0.02
    139
    +0.13
    0.02
    289
    +0.12
    0.01
    Negative Logits
    infty
    -1.75
    unnumbered
    -1.61
    odot
    -1.49
    rian
    -1.49
    las
    -1.43
    roll
    -1.41
    mail
    -1.38
    ness
    -1.35
     wait
    -1.33
    ubottu
    -1.32
    POSITIVE LOGITS
    hurst
    1.70
     Redistributions
    1.66
    enium
    1.66
     awarded
    1.61
    asant
    1.61
    lez
    1.61
    pective
    1.54
    venth
    1.53
    ene
    1.51
    stown
    1.44
    Activations Density 0.105%

    No Known Activations