© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 1-RES-SM
    11. 27952
    Prev
    Next
    INDEX
    Explanations

    the presence of capital letters or specific characters

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    156
    +0.26
    1.5%
    111
    +0.17
    1.0%
    17
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.26
    0.09
    271
    +0.17
    0.04
    17
    +0.14
    0.05
    Negative Logits
    dates
    -1.57
     Telescope
    -1.56
    Solution
    -1.30
     Last
    -1.29
    rings
    -1.29
     autom
    -1.28
    transform
    -1.26
     Intel
    -1.26
     Nation
    -1.26
    resolution
    -1.25
    POSITIVE LOGITS
     albicans
    1.82
     elegans
    1.68
    ^](#
    1.62
    ancel
    1.57
    ñor
    1.46
    abine
    1.46
    riber
    1.44
    uing
    1.39
    lez
    1.39
    ricular
    1.38
    Activations Density 0.122%

    No Known Activations