© 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. 27329
    Prev
    Next
    INDEX
    Explanations

    phrases associated with scientific research and academic topics

    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
    326
    +0.18
    1.1%
    271
    +0.14
    0.9%
    204
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    89
    +0.18
    0.08
    271
    +0.14
    -0.03
    204
    +0.13
    0.10
    Negative Logits
    Solve
    -1.58
    ership
    -1.56
    DEX
    -1.54
    giving
    -1.50
    Funding
    -1.50
     doors
    -1.49
    googleapis
    -1.49
    ):
    -1.49
    QUEST
    -1.49
    itations
    -1.46
    POSITIVE LOGITS
    ·
    3.10
    ¯
    2.92
    ĻĤ
    2.79
    ³
    2.74
    ħ
    2.72
    ¸
    2.72
    ľ
    2.66
    µ
    2.65
    «
    2.63
    ¿½
    2.55
    Activations Density 2.331%

    No Known Activations