© 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. 26610
    Prev
    Next
    INDEX
    Explanations

    references to software tools and applications

    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
    193
    +0.14
    0.8%
    184
    +0.14
    0.8%
    274
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    184
    +0.14
    0.02
    173
    +0.14
    0.02
    193
    +0.13
    0.02
    Negative Logits
    Ļª
    -2.31
    »¿
    -2.13
    ³
    -1.99
    áĢ¯
    -1.90
    §
    -1.87
    áĢº
    -1.86
    ¶
    -1.81
     vow
    -1.78
    ĥ
    -1.75
    ĨĴ
    -1.72
    POSITIVE LOGITS
    kit
    2.66
    tip
    2.55
    set
    2.23
    box
    2.21
    maker
    2.15
    bars
    2.12
    chain
    2.08
    table
    2.06
    bing
    1.93
    olver
    1.93
    Activations Density 0.141%

    No Known Activations