© 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. 25096
    Prev
    Next
    INDEX
    Explanations

    conversational questions and opinions expressed towards others

    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
    476
    +0.12
    0.7%
    309
    +0.10
    0.6%
    492
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    267
    +0.12
    0.03
    310
    +0.10
    0.03
    478
    +0.10
    0.00
    Negative Logits
    Ļª
    -2.16
    »
    -1.93
    ¼
    -1.89
    ´
    -1.89
    ¿½
    -1.78
    »¿
    -1.71
    ·¸
    -1.71
    ¡
    -1.69
    ģ
    -1.65
    ľĵ
    -1.62
    POSITIVE LOGITS
     curiosity
    1.50
     purpose
    1.36
     intention
    1.36
     Confederate
    1.34
     archae
    1.33
     intent
    1.33
     PTSD
    1.32
    StackTrace
    1.32
     tomb
    1.31
     humanity
    1.26
    Activations Density 0.678%

    No Known Activations