© 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. 28892
    Prev
    Next
    INDEX
    Explanations

    references to self-identity and personal experiences

    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
    23
    +0.14
    0.8%
    270
    +0.12
    0.7%
    81
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.14
    0.04
    478
    +0.12
    0.00
    328
    +0.11
    0.04
    Negative Logits
     specifics
    -1.68
    ISO
    -1.41
    imen
    -1.39
    mund
    -1.34
    clusive
    -1.32
    ):
    -1.31
    ilo
    -1.29
    aurus
    -1.29
     kits
    -1.28
     pieces
    -1.28
    POSITIVE LOGITS
     craving
    1.62
    hores
    1.58
    hus
    1.55
    omitempty
    1.52
     same
    1.46
    uron
    1.45
    anese
    1.44
    ertility
    1.44
    ?'
    1.44
    ffect
    1.43
    Activations Density 0.615%

    No Known Activations