© 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. 12690
    Prev
    Next
    INDEX
    Explanations

    segments of code or programming constructs involving definitions and requests

    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
    429
    +0.12
    0.7%
    384
    +0.12
    0.7%
    394
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    429
    +0.12
    0.03
    376
    +0.12
    0.00
    127
    +0.12
    0.06
    Negative Logits
    âĢIJ
    -1.49
    ahu
    -1.47
    ationally
    -1.46
    anian
    -1.45
    velopment
    -1.42
    aft
    -1.41
    ®
    -1.41
    ?_
    -1.39
    nis
    -1.38
    ?**
    -1.36
    POSITIVE LOGITS
     finally
    1.68
     trouble
    1.49
     concaten
    1.45
     rename
    1.45
    oo
    1.44
     confusion
    1.40
    ordinate
    1.35
     csv
    1.33
    encode
    1.33
    ême
    1.32
    Activations Density 0.610%

    No Known Activations