© 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. 31375
    Prev
    Next
    INDEX
    Explanations

    responses related to product creation and status checks

    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
    320
    +0.15
    0.9%
    63
    +0.13
    0.7%
    161
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    77
    +0.15
    0.03
    484
    +0.13
    0.07
    313
    +0.12
    0.06
    Negative Logits
    )$)
    -1.78
    "){
    -1.73
    anza
    -1.65
    ADVERTISEMENT
    -1.54
    ickets
    -1.52
    etica
    -1.47
    tone
    -1.46
    )">
    -1.45
    zig
    -1.40
    roc
    -1.40
    POSITIVE LOGITS
    ¹
    1.64
     Methodist
    1.59
     remotely
    1.51
    ured
    1.47
     Fellow
    1.46
    acular
    1.37
     vic
    1.36
     diastolic
    1.34
     interloc
    1.28
     surgeons
    1.26
    Activations Density 6.001%

    No Known Activations