© 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. 25916
    Prev
    Next
    INDEX
    Explanations

    terms and elements related to XML and software project configurations

    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
    111
    +0.21
    1.4%
    478
    +0.16
    1.0%
    466
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    157
    +0.21
    0.07
    315
    +0.16
    0.06
    71
    +0.13
    0.07
    Negative Logits
    aging
    -1.32
     recorded
    -1.27
     tracing
    -1.24
     established
    -1.24
     considering
    -1.23
    age
    -1.23
    pling
    -1.22
     EA
    -1.22
     scheduled
    -1.22
    ling
    -1.20
    POSITIVE LOGITS
    ĥ½
    1.80
    dimen
    1.60
    обÑĭ
    1.51
    лÑİ
    1.46
    оÐ
    1.42
    ubern
    1.42
    __)
    1.40
              ↵
    1.39
     ↵
    1.39
    ↵
    1.39
    Activations Density 0.591%

    No Known Activations