© 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. 28098
    Prev
    Next
    INDEX
    Explanations

    references to scopes in a programming or scripting context

    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
    459
    +0.12
    0.7%
    169
    +0.12
    0.7%
    250
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    179
    +0.12
    0.01
    169
    +0.12
    0.01
    73
    +0.11
    0.01
    Negative Logits
    ·¸
    -1.92
    iquity
    -1.86
    ĩ
    -1.79
    ĥ½
    -1.78
    ½
    -1.74
    ĵ
    -1.68
    documentclass
    -1.67
    ±
    -1.65
    ľĵ
    -1.65
    ----
    -1.58
    POSITIVE LOGITS
    ably
    1.73
    edly
    1.61
    ively
    1.56
     magazine
    1.53
     instruction
    1.50
     override
    1.50
     instructions
    1.49
     ammunition
    1.47
    nement
    1.47
    gun
    1.46
    Activations Density 0.104%

    No Known Activations