© 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. 1-RES-SM
    11. 28295
    Prev
    Next
    INDEX
    Explanations

    terms related to scanning and banners in software

    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
    441
    +0.13
    0.7%
    144
    +0.12
    0.7%
    169
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    262
    +0.13
    0.02
    169
    +0.12
    0.01
    144
    +0.12
    0.02
    Negative Logits
    ĺ
    -2.22
    ĵ
    -2.05
    ĥ½
    -1.79
    ķ
    -1.66
    rious
    -1.65
     particular
    -1.62
    Į
    -1.57
    IJ
    -1.57
    ģ
    -1.57
     separate
    -1.53
    POSITIVE LOGITS
    writer
    2.06
    wright
    2.02
    atura
    1.86
    optic
    1.85
    ão
    1.71
    ismo
    1.69
    ist
    1.69
    ovsk
    1.67
    glass
    1.67
    wort
    1.65
    Activations Density 0.121%

    No Known Activations