© 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. 28872
    Prev
    Next
    INDEX
    Explanations

    references to individuals or individualism within various contexts

    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
    156
    +0.23
    1.3%
    362
    +0.18
    1.0%
    282
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.23
    0.03
    357
    +0.18
    0.01
    282
    +0.10
    0.02
    Negative Logits
    roc
    -1.72
    rile
    -1.65
    ield
    -1.64
    mosp
    -1.54
    rous
    -1.52
    ril
    -1.46
    robe
    -1.41
    ound
    -1.39
    rian
    -1.39
    frastructure
    -1.38
    POSITIVE LOGITS
    ised
    2.07
    isations
    2.01
    ising
    1.85
    ity
    1.85
    itat
    1.85
    izing
    1.77
    ités
    1.77
    isation
    1.75
    itatively
    1.75
    iser
    1.72
    Activations Density 0.066%

    No Known Activations