© 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. 2-RES-SM
    11. 26725
    Prev
    Next
    INDEX
    Explanations

    expressions of personal feelings or relationships

    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
    326
    +0.13
    0.7%
    492
    +0.12
    0.7%
    310
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    81
    +0.13
    0.11
    100
    +0.12
    0.14
    219
    +0.12
    0.11
    Negative Logits
    ļ
    -1.97
    ħ
    -1.93
    İ
    -1.79
    tees
    -1.71
     extrinsic
    -1.66
     specifies
    -1.61
     {}
    -1.59
     union
    -1.52
    [^
    -1.52
     specify
    -1.51
    POSITIVE LOGITS
    Bye
    1.81
    odor
    1.78
     sorry
    1.78
     kidding
    1.73
    substack
    1.70
    upid
    1.63
    opsy
    1.63
    \]](
    1.56
    !_
    1.55
    à±ģ
    1.54
    Activations Density 4.503%

    No Known Activations