© 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. 2-RES-SM
    11. 10607
    Prev
    Next
    INDEX
    Explanations

    scientific terms related to chemical reactions and mechanisms

    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
    370
    +0.12
    0.7%
    23
    +0.11
    0.6%
    284
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.12
    0.31
    156
    +0.11
    0.28
    71
    +0.11
    0.27
    Negative Logits
    ontal
    -2.32
    findViewById
    -1.66
     worth
    -1.61
     Spacewatch
    -1.59
     internet
    -1.58
     monitor
    -1.53
    IDEO
    -1.53
     outlet
    -1.52
     GPS
    -1.52
     monitors
    -1.52
    POSITIVE LOGITS
    ĥ
    3.64
    IJ
    3.60
    ¸
    3.46
    µ
    3.41
    Ķ
    3.40
    ¿½
    3.40
    ħ
    3.39
    ľ
    3.36
    ¶
    3.31
    »¿
    3.25
    Activations Density 1.074%

    No Known Activations