© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 28649
    Prev
    Next
    INDEX
    Explanations

    nested structures or elements in a document

    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
    410
    +0.13
    0.7%
    478
    +0.12
    0.7%
    51
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    175
    +0.13
    0.03
    51
    +0.12
    0.03
    341
    +0.12
    0.03
    Negative Logits
    illin
    -1.66
    ite
    -1.60
    around
    -1.54
    augh
    -1.54
    ually
    -1.45
    wise
    -1.44
    rew
    -1.38
    .[]{
    -1.35
    inating
    -1.32
    istically
    -1.32
    POSITIVE LOGITS
    IJ
    3.68
    ¡
    3.49
    ij
    3.38
    ĨĴ
    3.35
    ĥ½
    3.35
    ķ
    3.31
    ļ
    3.24
    »
    3.23
    ¥
    3.22
    ĸ
    3.16
    Activations Density 0.100%

    No Known Activations