© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 2-RES-SM
    11. 10530
    Prev
    Next
    INDEX
    Explanations

    terms related to bending, flexibility, and physical manipulation of objects

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    328
    +0.13
    0.7%
    32
    +0.12
    0.7%
    361
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    148
    +0.13
    0.01
    115
    +0.12
    0.04
    32
    +0.11
    0.03
    Negative Logits
     sponsors
    -1.71
     Ethics
    -1.67
     trusted
    -1.60
     Office
    -1.55
     computers
    -1.54
     publisher
    -1.52
     Director
    -1.49
     mention
    -1.47
     Affairs
    -1.47
     dissemination
    -1.46
    POSITIVE LOGITS
    ĩ
    2.40
    ĻĤ
    2.24
    Ģ
    2.12
    ŀ
    2.05
    ĨĴ
    2.04
    orphic
    2.02
    į
    1.99
    Ĵ
    1.94
    ij
    1.91
    horn
    1.82
    Activations Density 0.491%

    No Known Activations