© 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. 27797
    Prev
    Next
    INDEX
    Explanations

    HTML comments

    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
    71
    +0.14
    0.8%
    42
    +0.13
    0.7%
    231
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    42
    +0.14
    0.01
    315
    +0.13
    0.01
    399
    +0.12
    0.01
    Negative Logits
    otts
    -1.54
    uries
    -1.51
    rait
    -1.48
    res
    -1.44
    yan
    -1.43
    urns
    -1.42
     farms
    -1.41
     theory
    -1.41
     succession
    -1.41
     recovery
    -1.40
    POSITIVE LOGITS
    TRODUCTION
    1.72
    TeX
    1.65
     GENERATED
    1.57
    TOD
    1.53
     TODO
    1.51
     Comments
    1.48
    ]:
    1.46
    ^](#
    1.45
    izontal
    1.45
     NOTE
    1.45
    Activations Density 0.054%

    No Known Activations