© 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. 28841
    Prev
    Next
    INDEX
    Explanations

    legal jargon and procedural terminology

    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
    156
    +0.15
    0.8%
    425
    +0.13
    0.7%
    42
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.15
    0.07
    271
    +0.13
    0.02
    17
    +0.12
    0.04
    Negative Logits
     fork
    -1.60
    ahead
    -1.59
     anymore
    -1.49
     sheet
    -1.46
    .[]{
    -1.46
     sheets
    -1.46
     prerequisite
    -1.41
     version
    -1.39
     checkpoint
    -1.38
    ."""
    -1.35
    POSITIVE LOGITS
    dered
    1.44
    verte
    1.39
    oyd
    1.37
    ldots
    1.36
    igm
    1.36
    vae
    1.34
     prol
    1.32
    itching
    1.32
    abine
    1.32
     Population
    1.31
    Activations Density 0.171%

    No Known Activations