© 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 EvalsExportsinterp-engineNEWAPI 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. 28036
    Prev
    Next
    INDEX
    Explanations

    terms related to service definitions and their operational elements

    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
    17
    +0.17
    1.0%
    83
    +0.13
    0.7%
    248
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    83
    +0.17
    0.07
    17
    +0.13
    -0.02
    57
    +0.12
    0.10
    Negative Logits
    asty
    -2.01
     proud
    -1.44
     actress
    -1.41
     happy
    -1.41
    ucky
    -1.36
     country
    -1.33
    vious
    -1.30
     ice
    -1.29
    umatic
    -1.29
    orous
    -1.27
    POSITIVE LOGITS
    ¢
    1.62
    /~
    1.56
    vez
    1.54
     adjacent
    1.52
    ¬
    1.51
    ĥ½
    1.51
    ¯
    1.47
    £
    1.46
    .[]{
    1.45
    proportion
    1.45
    Activations Density 4.826%

    No Known Activations