© 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. 27714
    Prev
    Next
    INDEX
    Explanations

    specific numerical and structural elements in technical or formal contexts

    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
    144
    +0.13
    0.7%
    259
    +0.13
    0.7%
    344
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.13
    0.01
    271
    +0.13
    0.00
    17
    +0.12
    0.01
    Negative Logits
    ably
    -1.78
    eth
    -1.77
    aneously
    -1.52
     ought
    -1.46
    cause
    -1.46
    unal
    -1.42
    earing
    -1.42
     panels
    -1.41
    mente
    -1.40
    jack
    -1.40
    POSITIVE LOGITS
    ynchron
    1.59
    ↵³³
    1.59
    iew
    1.55
    []{
    1.46
    rei
    1.44
    ename
    1.42
    oscopic
    1.41
    mology
    1.39
    ympt
    1.37
    nt
    1.37
    Activations Density 0.001%

    No Known Activations