© 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. 13474
    Prev
    Next
    INDEX
    Explanations

    references to significant consequences or impacts on individuals or society

    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
    255
    +0.12
    0.7%
    478
    +0.11
    0.6%
    299
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    255
    +0.12
    0.12
    418
    +0.11
    0.01
    266
    +0.10
    0.09
    Negative Logits
    vendor
    -1.56
    ]:
    -1.48
    "}](#
    -1.44
    bol
    -1.40
     volt
    -1.39
    \])]{}
    -1.38
    azard
    -1.36
    assen
    -1.34
    bound
    -1.33
    ayers
    -1.33
    POSITIVE LOGITS
    Ī
    2.08
    1.77
     ↵
    1.77
    1.77
    ↵
    1.77
    1.77
              ↵
    1.77
             ↵
    1.77
    1.77
    č↵
    1.77
    Activations Density 0.886%

    No Known Activations