© 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. 28121
    Prev
    Next
    INDEX
    Explanations

    XML configuration properties related to software projects

    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
    271
    +0.14
    0.8%
    360
    +0.12
    0.7%
    71
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    416
    +0.14
    0.04
    157
    +0.12
    0.07
    252
    +0.12
    0.04
    Negative Logits
     respectively
    -1.75
    respectively
    -1.52
     ‘
    -1.39
    onde
    -1.39
     intervals
    -1.39
    :--
    -1.38
     witnessed
    -1.35
     anatom
    -1.34
     opposite
    -1.34
     accord
    -1.33
    POSITIVE LOGITS
    aml
    1.66
    оÐ
    1.57
    utor
    1.54
    алÑĮ
    1.45
     Release
    1.45
    č
    1.45
    ederal
    1.44
    ortun
    1.43
    ")]
    1.41
    иÑĢ
    1.39
    Activations Density 0.667%

    No Known Activations