© 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. 29009
    Prev
    Next
    INDEX
    Explanations

    references to interpersonal relationships and moral implications regarding behavior

    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
    441
    +0.16
    0.9%
    17
    +0.12
    0.7%
    232
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    427
    +0.16
    0.04
    441
    +0.12
    0.01
    232
    +0.12
    0.07
    Negative Logits
    ppat
    -1.73
    available
    -1.66
    pntd
    -1.65
    pgen
    -1.59
    idone
    -1.57
    oses
    -1.54
    icense
    -1.51
     available
    -1.49
    lein
    -1.47
    orts
    -1.47
    POSITIVE LOGITS
    Ĩ
    2.31
    «
    2.25
    ı
    2.19
    ¿½
    2.02
    ħ
    1.99
    ·¸
    1.94
    ĻĤ
    1.91
    İ
    1.90
    Īĺ
    1.90
    ↵↵
    1.85
    Activations Density 2.756%

    No Known Activations